© 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. 7224
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to urban development and geography

    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
    87
    +0.18
    0.9%
    459
    +0.09
    0.5%
    155
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.07
    365
    +0.09
    0.03
    659
    +0.09
    0.06
    Negative Logits
     AND
    -0.58
     looph
    -0.53
    hematically
    -0.51
     TODAY
    -0.51
     today
    -0.50
    ãĤ°
    -0.50
     indeed
    -0.49
     and
    -0.48
     compile
    -0.46
    Adds
    -0.46
    POSITIVE LOGITS
     respectively
    1.01
     alike
    0.89
     thereof
    0.85
     thereto
    0.78
     versa
    0.77
     thereafter
    0.66
    cellaneous
    0.64
     therein
    0.58
    Ħ¢
    0.58
     LLP
    0.57
    Activations Density 0.881%

    No Known Activations