© 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. 45512
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'z' in various contexts

    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
    314
    +0.13
    0.6%
    648
    +0.10
    0.5%
    113
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    284
    +0.10
    0.02
    585
    +0.10
    0.02
    Negative Logits
     Columb
    -0.64
     laure
    -0.63
    OPLE
    -0.60
    BILITY
    -0.59
    Interstitial
    -0.59
    ãģ®éŃĶ
    -0.58
     ransom
    -0.58
    fty
    -0.55
     Cardinal
    -0.55
    enment
    -0.54
    POSITIVE LOGITS
    ombie
    1.05
    uka
    0.93
    uyomi
    0.92
    hao
    0.91
    uko
    0.90
    hang
    0.87
    ulk
    0.86
    ombies
    0.86
    alez
    0.86
    ozo
    0.84
    Activations Density 0.019%

    No Known Activations