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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 221
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and introspection

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    362
    +0.13
    0.6%
    408
    +0.10
    0.4%
    372
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.13
    0.03
    743
    +0.10
    0.03
    362
    +0.10
    0.03
    Negative Logits
    olic
    -0.78
     Dates
    -0.71
    naire
    -0.70
    lehem
    -0.70
    ol
    -0.69
    ievers
    -0.68
    ————————
    -0.67
    osi
    -0.66
    ummer
    -0.65
    zai
    -0.65
    POSITIVE LOGITS
     personal
    0.93
     backyard
    0.90
     accord
    0.88
     creations
    0.84
     selves
    0.83
     interests
    0.81
     admission
    0.79
     feelings
    0.77
     affairs
    0.75
     demise
    0.73
    Activations Density 0.047%

    No Known Activations