© 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 49152
    9. 8-RES_FS49152-JB
    11. 41709
    Prev
    Next
    INDEX
    Explanations

    words indicating certainty or frequency of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    551
    +0.13
    0.6%
    13
    +0.10
    0.5%
    699
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.13
    0.03
    466
    +0.10
    0.02
    718
    +0.09
    0.02
    Negative Logits
     Wid
    -0.65
    quickShipAvailable
    -0.64
     continents
    -0.64
     infiltration
    -0.63
     Ips
    -0.63
     Hanson
    -0.63
     puzzles
    -0.61
     Niet
    -0.59
     ROS
    -0.59
     Cir
    -0.59
    POSITIVE LOGITS
     emulate
    1.04
     beware
    0.99
     be
    0.98
     consider
    0.97
     strive
    0.93
     aspire
    0.91
     disclose
    0.86
     behave
    0.85
     consult
    0.85
     allocate
    0.84
    Activations Density 0.046%

    No Known Activations