© 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. 26543
    Prev
    Next
    INDEX
    Explanations

    mentions of skulls or related imagery

    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
    549
    +0.13
    0.6%
    99
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    549
    +0.13
    0.01
    181
    +0.12
    0.01
    Negative Logits
    ARY
    -0.69
     Opportun
    -0.66
    Avg
    -0.66
    Published
    -0.66
     NCT
    -0.65
     Supporters
    -0.65
    YN
    -0.64
    agonist
    -0.63
    bidden
    -0.63
     Idle
    -0.63
    POSITIVE LOGITS
    bones
    1.06
    bone
    1.01
     skull
    1.01
    cap
    1.00
     skulls
    0.92
     bones
    0.91
    caps
    0.89
     fracture
    0.87
     fractures
    0.86
     ornament
    0.81
    Activations Density 0.005%

    No Known Activations