Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11245
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    133
    +0.14
    0.6%
    408
    +0.13
    0.6%
    245
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.14
    0.04
    133
    +0.13
    0.04
    412
    +0.10
    0.03
    Negative Logits
    wcsstore
    -0.94
    xual
    -0.76
    anson
    -0.73
    antom
    -0.71
    potion
    -0.70
     Emails
    -0.68
     Subcommittee
    -0.67
    rodu
    -0.67
    olson
    -0.67
    ulty
    -0.66
    POSITIVE LOGITS
     Abu
    0.85
     suburbs
    0.82
     suburb
    0.81
     Tripoli
    0.81
     Marse
    0.79
     Alexandria
    0.78
     Jerusalem
    0.78
     Bam
    0.77
     Aleppo
    0.77
     Mosul
    0.77
    Activations Density 0.082%

    No Known Activations