© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26682
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "anomaly" and its variants

    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
    642
    +0.13
    0.6%
    195
    +0.13
    0.6%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.01
    284
    +0.13
    0.01
    116
    +0.12
    0.01
    Negative Logits
    glers
    -0.84
    lasses
    -0.79
    sonian
    -0.78
    shaw
    -0.71
    utive
    -0.71
    apest
    -0.71
    fax
    -0.70
    ledge
    -0.70
    hens
    -0.69
    ingers
    -0.68
    POSITIVE LOGITS
    ous
    0.98
    istically
    0.90
    ously
    0.89
     recess
    0.78
     occ
    0.74
     Vie
    0.72
    istics
    0.70
     Detected
    0.69
    istic
    0.69
    bum
    0.68
    Activations Density 0.019%

    No Known Activations