© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10936
    Prev
    Next
    INDEX
    Explanations

    information related to the structure and components of the brain, particularly neurons, synapses, and their connections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.49
    2.5%
    7
    +0.12
    0.6%
    266
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.02
    266
    +0.12
    0.09
    7
    +0.12
    0.06
    Negative Logits
    >]
    -0.59
    tein
    -0.58
     beforehand
    -0.58
    Ther
    -0.55
     Pipe
    -0.55
     withdrew
    -0.55
    ]."
    -0.54
    IDA
    -0.54
     adv
    -0.54
    Alternatively
    -0.54
    POSITIVE LOGITS
     remarkably
    0.74
     fundamentally
    0.74
    htaking
    0.72
     fascinated
    0.71
     profoundly
    0.71
     unquestion
    0.69
     uniquely
    0.68
     fascinating
    0.67
     remarkable
    0.66
     undeniably
    0.66
    Activations Density 1.086%

    No Known Activations