© 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 49152
    9. 8-RES_FS49152-JB
    11. 41706
    Prev
    Next
    INDEX
    Explanations

    references to hexagonal structures or shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.13
    0.6%
    553
    +0.12
    0.6%
    651
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.13
    0.01
    651
    +0.12
    0.01
    289
    +0.12
    0.01
    Negative Logits
    Interstitial
    -0.94
    HCR
    -0.76
     Crowd
    -0.74
    utenant
    -0.71
     Responsibility
    -0.70
     conditioning
    -0.69
     Strateg
    -0.68
     LAST
    -0.68
    jriwal
    -0.67
    ãģĦ
    -0.67
    POSITIVE LOGITS
    agonal
    1.74
    agon
    1.37
    agons
    1.20
    agram
    1.06
    aval
    0.99
    angular
    0.96
    hex
    0.95
    ade
    0.91
    ile
    0.90
    dump
    0.88
    Activations Density 0.005%

    No Known Activations