Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 839
    Prev
    Next
    INDEX
    Explanations

    organizations and entities related to government and agencies

    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
    627
    +0.12
    0.6%
    364
    +0.10
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.12
    0.04
    388
    +0.10
    0.04
    627
    +0.09
    0.03
    Negative Logits
     weap
    -0.70
    quickShipAvailable
    -0.68
     unden
    -0.67
     captcha
    -0.65
     tremend
    -0.62
    taboola
    -0.61
     showc
    -0.61
    izoph
    -0.59
    catentry
    -0.58
     piston
    -0.58
    POSITIVE LOGITS
    )
    1.33
    ),
    1.32
    )'
    1.23
    )—
    1.18
    ).
    1.10
    )[
    1.07
    )),
    1.01
    )-
    1.01
    )?
    1.00
    ),"
    1.00
    Activations Density 0.065%

    No Known Activations