© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    detailed information and updates on current events, legal matters, or government actions

    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
    389
    +0.13
    0.6%
    191
    +0.10
    0.5%
    455
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.13
    0.06
    455
    +0.10
    0.06
    190
    +0.10
    0.05
    Negative Logits
     Unlock
    -0.70
    DK
    -0.63
    DD
    -0.62
    de
    -0.62
    AE
    -0.62
     Freeze
    -0.59
     Advis
    -0.59
    Ds
    -0.59
    mberg
    -0.59
     Moves
    -0.59
    POSITIVE LOGITS
     than
    1.42
    ened
    1.21
    ening
    1.14
     Than
    0.91
    than
    0.90
     forgiving
    0.89
     fortunate
    0.88
     stringent
    0.88
    ens
    0.84
    thumbnails
    0.82
    Activations Density 0.279%

    No Known Activations