© 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. 37264
    Prev
    Next
    INDEX
    Explanations

    references to professors or academic titles

    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%
    575
    +0.12
    0.5%
    90
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.13
    0.01
    462
    +0.12
    0.01
    60
    +0.11
    0.01
    Negative Logits
    MENTS
    -0.80
    doors
    -0.74
     Nebula
    -0.68
     halfway
    -0.65
    MENT
    -0.63
     Mali
    -0.63
     Blazers
    -0.63
    wolves
    -0.62
    boat
    -0.62
     PAL
    -0.61
    POSITIVE LOGITS
    essor
    1.70
    iciency
    1.46
    ession
    1.40
    iles
    1.35
    essors
    1.34
    ound
    1.30
    icient
    1.26
    essed
    1.16
    iling
    1.15
    iled
    1.12
    Activations Density 0.003%

    No Known Activations