© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    words related to locations

    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
    267
    +0.12
    0.6%
    527
    +0.11
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.12
    0.01
    406
    +0.11
    0.01
    99
    +0.10
    0.01
    Negative Logits
    ãĤ¶
    -0.80
    senal
    -0.77
    ADRA
    -0.74
     membr
    -0.74
    ploma
    -0.72
    abeth
    -0.71
     Catalyst
    -0.70
     âĶľ
    -0.69
    enegger
    -0.67
    OPLE
    -0.66
    POSITIVE LOGITS
    sburg
    1.14
    s
    0.98
    ership
    0.89
    ski
    0.88
    icative
    0.87
    icz
    0.86
    ess
    0.84
    lishing
    0.83
    e
    0.82
    yk
    0.82
    Activations Density 0.024%

    No Known Activations