© 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. 26567
    Prev
    Next
    INDEX
    Explanations

    the word "per" in various contexts

    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
    509
    +0.09
    0.4%
    225
    +0.09
    0.4%
    176
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.09
    0.02
    82
    +0.09
    0.02
    583
    +0.09
    0.01
    Negative Logits
    ARDIS
    -0.69
    MpServer
    -0.65
    å¦
    -0.60
     shortened
    -0.60
    externalActionCode
    -0.56
     postponed
    -0.56
     GOODMAN
    -0.55
    enez
    -0.54
     rook
    -0.54
    abs
    -0.54
    POSITIVE LOGITS
    tains
    1.07
     capita
    1.05
    malink
    0.93
    versely
    0.92
    tained
    0.89
    severe
    0.85
    tain
    0.82
    verted
    0.78
    verting
    0.76
    ishable
    0.75
    Activations Density 0.013%

    No Known Activations