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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 5403
    Prev
    Next
    INDEX
    Explanations

    actions related to physical violence and assault

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    419
    +0.14
    0.6%
    678
    +0.12
    0.5%
    371
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.08
    371
    +0.12
    0.07
    526
    +0.11
    0.00
    Negative Logits
     specialization
    -0.82
    ontent
    -0.78
     unemploy
    -0.72
     optimization
    -0.71
     Optim
    -0.66
     specialize
    -0.66
     Colomb
    -0.65
    CLUS
    -0.65
     specialists
    -0.65
     Revenue
    -0.64
    POSITIVE LOGITS
    stretched
    1.30
     gently
    1.18
     clasp
    1.18
     grasped
    1.13
     hips
    1.11
     clenched
    1.10
     knees
    1.09
     waist
    1.07
     fingers
    1.07
     zipper
    1.05
    Activations Density 1.052%

    No Known Activations