© 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 24576
    9. 8-RES_FS24576-JB
    11. 9649
    Prev
    Next
    INDEX
    Explanations

    sentences starting with 'That' followed by new information or development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    274
    +0.11
    0.5%
    321
    +0.11
    0.5%
    159
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.11
    0.07
    662
    +0.11
    0.06
    598
    +0.10
    0.04
    Negative Logits
    hat
    -0.81
    hops
    -0.76
    emis
    -0.74
    natureconservancy
    -0.74
    perse
    -0.73
    pots
    -0.72
    ARCH
    -0.69
    velop
    -0.69
    ãĥĥãĤ¯
    -0.67
    hin
    -0.66
    POSITIVE LOGITS
     resulted
    1.22
     amounted
    1.04
     culminated
    1.02
     latter
    1.02
     prompted
    0.99
     includes
    0.95
     consisted
    0.93
     occurred
    0.93
     translates
    0.93
     coincided
    0.93
    Activations Density 0.145%

    No Known Activations