© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    keywords related to social issues and analysis of societal structures

    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
    480
    +0.39
    1.9%
    447
    +0.23
    1.1%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.39
    -0.01
    598
    +0.23
    0.04
    563
    +0.11
    0.07
    Negative Logits
    Flying
    -0.65
    emate
    -0.64
    dead
    -0.64
    Yep
    -0.63
    Enlarge
    -0.63
    ascal
    -0.60
    UPDATE
    -0.59
    perty
    -0.59
    uminium
    -0.58
    veyard
    -0.58
    POSITIVE LOGITS
     strives
    0.84
     emphasizes
    0.82
     strive
    0.81
     explores
    0.81
     insightful
    0.81
     insights
    0.80
     concise
    0.79
     insight
    0.76
     integrates
    0.76
     mentors
    0.76
    Activations Density 1.523%

    No Known Activations