© 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. 18788
    Prev
    Next
    INDEX
    Explanations

    references to dolls

    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
    383
    +0.13
    0.6%
    213
    +0.11
    0.5%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    659
    +0.11
    0.01
    122
    +0.11
    0.01
    Negative Logits
    ãĥ¥
    -0.81
    TAIN
    -0.79
    ################
    -0.77
    EED
    -0.76
    ãĤ¡
    -0.72
    riott
    -0.71
    llah
    -0.71
    ELY
    -0.71
    GGGGGGGG
    -0.69
    NING
    -0.69
    POSITIVE LOGITS
     doll
    0.97
    maker
    0.95
     dolls
    0.88
    enger
    0.84
    houses
    0.83
    ies
    0.81
    house
    0.81
    ophone
    0.81
    oning
    0.78
    omb
    0.74
    Activations Density 0.023%

    No Known Activations