© 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. 18790
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographical locations, such as cities and regions

    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
    220
    +0.10
    0.4%
    631
    +0.10
    0.4%
    234
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.10
    0.02
    140
    +0.10
    0.02
    631
    +0.09
    0.02
    Negative Logits
    rador
    -0.78
    azines
    -0.71
    imately
    -0.67
    antha
    -0.64
     Ples
    -0.64
    pai
    -0.64
    pick
    -0.64
     Leilan
    -0.63
     monop
    -0.63
     glide
    -0.63
    POSITIVE LOGITS
    yond
    1.44
    arer
    1.11
    arers
    1.09
    FORE
    1.07
    cker
    1.04
    zos
    1.03
    xt
    0.99
    hemoth
    0.96
    gotten
    0.94
    agle
    0.94
    Activations Density 0.024%

    No Known Activations