© 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. 37358
    Prev
    Next
    INDEX
    Explanations

    terms related to shallowness or superficiality

    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
    195
    +0.12
    0.6%
    238
    +0.10
    0.5%
    67
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.12
    0.01
    99
    +0.10
    0.01
    669
    +0.09
    0.01
    Negative Logits
    CLASSIFIED
    -0.75
    OX
    -0.70
     starring
    -0.70
    haw
    -0.69
    signed
    -0.68
    Revolution
    -0.68
    unknown
    -0.67
    FORE
    -0.66
    HCR
    -0.66
     Chronicles
    -0.63
    POSITIVE LOGITS
    est
    1.03
    ly
    1.01
     (<
    0.90
    ened
    0.88
     shallow
    0.88
    ening
    0.87
     slope
    0.83
     depth
    0.81
    itudinal
    0.81
    ness
    0.80
    Activations Density 0.004%

    No Known Activations