© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    elements related to locations or descriptions of physical objects in a specific setting

    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
    +0.39
    1.9%
    481
    +0.28
    1.4%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.39
    0.02
    266
    +0.28
    0.07
    288
    +0.14
    0.08
    Negative Logits
     contracted
    -0.64
    authorized
    -0.62
     agre
    -0.62
     Instr
    -0.61
     destro
    -0.60
    Specific
    -0.60
    levant
    -0.58
    Fac
    -0.58
     livest
    -0.58
    spec
    -0.57
    POSITIVE LOGITS
    !
    0.98
    !:
    0.95
    ?!
    0.92
    !?
    0.91
     huh
    0.88
    !!
    0.84
    !!!
    0.84
    !'
    0.84
    !!!!
    0.83
    ?
    0.79
    Activations Density 0.625%

    No Known Activations