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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 3068
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-identity and personal development

    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
    635
    +0.12
    0.5%
    323
    +0.10
    0.5%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    635
    +0.12
    0.04
    323
    +0.10
    0.04
    246
    +0.09
    0.04
    Negative Logits
     Nights
    -0.77
     Ashe
    -0.75
     XIII
    -0.72
    ī
    -0.70
     GOODMAN
    -0.69
     Rouge
    -0.68
     Syndicate
    -0.68
    SHIP
    -0.67
     CES
    -0.65
    IUM
    -0.65
    POSITIVE LOGITS
    destruct
    1.29
    same
    1.05
    conscious
    0.99
    ridges
    0.97
    lessly
    0.97
     destruct
    0.97
    contained
    0.91
     explanatory
    0.90
     esteem
    0.86
    proclaimed
    0.85
    Activations Density 0.369%

    No Known Activations