© 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 12288
    9. 8-RES_FS12288-JB
    11. 10154
    Prev
    Next
    INDEX
    Explanations

    mentions of international conferences and meetings

    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
    257
    +0.14
    0.6%
    640
    +0.12
    0.6%
    123
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.14
    0.07
    123
    +0.12
    0.07
    469
    +0.12
    0.06
    Negative Logits
    gans
    -0.78
    CLASSIFIED
    -0.74
     %%
    -0.71
    esian
    -0.71
    username
    -0.67
    Choice
    -0.67
     ingred
    -0.66
    ystem
    -0.65
    /(
    -0.64
    Current
    -0.64
    POSITIVE LOGITS
     conjunction
    1.26
     Cannes
    1.14
     Tokyo
    1.10
     Seoul
    1.09
     Frankfurt
    1.06
     Paris
    1.04
     Rome
    1.03
     Brussels
    1.03
     Prague
    1.02
     lieu
    1.02
    Activations Density 0.256%

    No Known Activations