© 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. 37394
    Prev
    Next
    INDEX
    Explanations

    instances of the word "later."

    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
    237
    +0.11
    0.5%
    132
    +0.10
    0.4%
    696
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.11
    0.02
    237
    +0.10
    0.02
    296
    +0.10
    0.02
    Negative Logits
     Pwr
    -0.76
    Merit
    -0.73
    ³³³³³³³³³³³³³³³³
    -0.65
    PORT
    -0.65
    advertising
    -0.61
     Flavoring
    -0.60
    ³³³³³³³³
    -0.60
     Fist
    -0.58
    chery
    -0.58
    BAT
    -0.58
    POSITIVE LOGITS
    ally
    1.20
    etheless
    1.07
    aneously
    0.93
    ality
    0.89
    iations
    0.89
    iation
    0.83
    iated
    0.82
     phases
    0.80
    alities
    0.79
     generations
    0.79
    Activations Density 0.024%

    No Known Activations