© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10423
    Prev
    Next
    INDEX
    Explanations

    mentions of access and associated actions such as accessing, with a particularly high activation for the word "Access."

    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
    365
    +0.13
    0.6%
    496
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.13
    0.03
    365
    +0.11
    0.02
    271
    +0.11
    0.03
    Negative Logits
     Kern
    -0.87
    Maker
    -0.63
     bulls
    -0.62
     farewell
    -0.60
     Saud
    -0.59
     abst
    -0.57
    Lens
    -0.57
     stride
    -0.56
     almond
    -0.56
     estranged
    -0.56
    POSITIVE LOGITS
    ibility
    1.45
    ibly
    1.34
    ible
    1.21
    ory
    1.02
    ioned
    0.99
    ibl
    0.99
    ibles
    0.97
    ibilities
    0.96
    IBLE
    0.93
    ories
    0.92
    Activations Density 0.062%

    No Known Activations