© 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. 8570
    Prev
    Next
    INDEX
    Explanations

    specific words in a text, focusing on words rather than the context or structure of the sentences

    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
    289
    +0.10
    0.5%
    623
    +0.09
    0.4%
    481
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.10
    0.01
    623
    +0.09
    0.02
    435
    +0.08
    0.02
    Negative Logits
    DERR
    -0.96
    roxy
    -0.83
    taboola
    -0.77
    ©¶æ¥µ
    -0.75
    psey
    -0.75
    abama
    -0.72
    ersen
    -0.72
    rero
    -0.71
    ahon
    -0.70
     Democr
    -0.70
    POSITIVE LOGITS
    mith
    1.17
    sworth
    1.08
     ptr
    0.93
    ifier
    0.89
    press
    0.82
     diction
    0.80
     phrases
    0.79
     uttered
    0.79
    words
    0.79
    processor
    0.78
    Activations Density 0.040%

    No Known Activations