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

    Neuronpedia

    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. 18485
    Prev
    Next
    INDEX
    Explanations

    mentions of funding or financial resources related to projects

    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
    481
    +0.31
    1.6%
    480
    +0.25
    1.3%
    447
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.31
    0.07
    266
    +0.25
    0.05
    480
    +0.20
    0.02
    Negative Logits
     challeng
    -0.62
     seiz
    -0.61
     prest
    -0.61
     territ
    -0.60
     Jagu
    -0.60
    emale
    -0.58
    avorite
    -0.57
     Gaw
    -0.55
     contrace
    -0.55
     behav
    -0.54
    POSITIVE LOGITS
    Joined
    0.70
    ¶
    0.67
    resses
    0.66
    =\"
    0.63
     ][
    0.62
     ]
    0.61
    coins
    0.60
    ="
    0.60
     returns
    0.59
     ==
    0.59
    Activations Density 0.246%

    No Known Activations