© 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. 41678
    Prev
    Next
    INDEX
    Explanations

    expressions of strong enthusiasm or fandom

    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
    353
    +0.11
    0.5%
    517
    +0.10
    0.5%
    230
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.11
    0.03
    331
    +0.10
    0.03
    353
    +0.10
    0.02
    Negative Logits
    querade
    -0.68
    ousands
    -0.65
    alion
    -0.65
    Sov
    -0.65
     imprisonment
    -0.64
     subsequ
    -0.64
    çķ
    -0.64
     omin
    -0.64
     trillions
    -0.63
     vacancies
    -0.63
    POSITIVE LOGITS
     obsessed
    0.98
     interested
    0.96
     admire
    0.93
     believer
    0.93
     proponent
    0.93
     fan
    0.92
     avid
    0.91
     keen
    0.91
     diabetic
    0.86
     obsessive
    0.85
    Activations Density 0.103%

    No Known Activations