© 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 1536
    9. 8-RES_FS1536-JB
    11. 62
    Prev
    Next
    INDEX
    Explanations

    technical explanations and descriptions, such as those found in scientific articles or engineering reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    447
    +0.11
    0.5%
    712
    +0.10
    0.5%
    84
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.11
    0.12
    55
    +0.10
    0.17
    566
    +0.10
    0.13
    Negative Logits
     Anger
    -0.74
     Chiefs
    -0.68
     gulf
    -0.66
     Wolves
    -0.64
     perspectives
    -0.64
     perspective
    -0.63
     Letters
    -0.62
     Factors
    -0.62
    mental
    -0.62
    Marie
    -0.62
    POSITIVE LOGITS
     operated
    1.22
     marketed
    1.17
     outper
    1.10
     housed
    1.05
     usable
    1.04
     functionally
    1.02
     commercially
    1.01
     capable
    1.00
     powered
    0.99
     designed
    0.97
    Activations Density 4.976%

    No Known Activations