© 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 24576
    9. 8-RES_FS24576-JB
    11. 18934
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban areas or cities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    167
    +0.11
    0.5%
    219
    +0.10
    0.5%
    152
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.11
    0.04
    152
    +0.10
    0.04
    76
    +0.09
    0.04
    Negative Logits
    imilar
    -0.81
    zees
    -0.78
    pmwiki
    -0.78
    etsk
    -0.77
    iotic
    -0.76
    essee
    -0.76
    uchin
    -0.73
    cue
    -0.72
    SourceFile
    -0.71
    sembly
    -0.70
    POSITIVE LOGITS
    scape
    1.34
     skyline
    1.22
    wide
    1.13
     council
    1.04
     streets
    1.02
     councillor
    1.00
     hall
    0.94
     halls
    0.92
     councils
    0.91
     dwell
    0.90
    Activations Density 0.063%

    No Known Activations