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 3072
    5. 8-RES_FS3072-JB
    6. 428
    Prev
    Next
    INDEX
    Explanations

    mentions and references to specific names and topics in written content, likely from social media or news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    107
    +0.12
    0.5%
    442
    +0.11
    0.5%
    158
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.07
    284
    +0.11
    0.08
    326
    +0.10
    0.08
    Negative Logits
     cumbers
    -0.80
     outsiders
    -0.70
     embargo
    -0.69
     exha
    -0.68
     breadth
    -0.68
     salient
    -0.68
     passage
    -0.67
     carbohyd
    -0.67
     bree
    -0.66
     increment
    -0.66
    POSITIVE LOGITS
    _-_
    1.30
    _
    1.28
    _(
    1.22
    _.
    1.21
    __
    1.20
    @
    1.18
    Jr
    1.14
    ()
    1.08
    /,
    0.99
    Stud
    0.99
    Activations Density 0.907%

    No Known Activations