© 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 12288
    9. 8-RES_FS12288-JB
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, software, and economic terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    174
    +0.12
    0.5%
    362
    +0.11
    0.5%
    600
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.12
    0.05
    288
    +0.11
    0.07
    174
    +0.10
    0.05
    Negative Logits
    cius
    -0.80
    RAW
    -0.79
    irlf
    -0.76
    aido
    -0.76
    pora
    -0.75
    Alias
    -0.72
    uca
    -0.70
    Scroll
    -0.70
    ONEY
    -0.69
    OST
    -0.69
    POSITIVE LOGITS
    tenance
    0.87
     hybrid
    0.81
     goodness
    0.78
    osterone
    0.78
     hybrids
    0.77
    ing
    0.71
    ning
    0.69
     extraord
    0.69
    quartered
    0.68
     continuum
    0.67
    Activations Density 0.416%

    No Known Activations