© 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 1536
    9. 8-RES_FS1536-JB
    11. 1130
    Prev
    Next
    INDEX
    Explanations

    gender-related characteristics and attitudes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    515
    +0.11
    0.5%
    430
    +0.10
    0.5%
    276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.11
    0.08
    660
    +0.10
    0.06
    325
    +0.10
    0.07
    Negative Logits
    REDACTED
    -0.83
    Assembly
    -0.74
    REC
    -0.72
    IVERS
    -0.71
    Deal
    -0.67
    KEN
    -0.66
    RAY
    -0.64
    ENC
    -0.63
    ITS
    -0.63
    VICE
    -0.62
    POSITIVE LOGITS
    volent
    1.41
    opausal
    1.17
    hood
    1.05
    ager
    0.99
    uscript
    0.99
    folk
    0.95
    agers
    0.94
    gling
    0.91
    stru
    0.90
    hunt
    0.90
    Activations Density 1.153%

    No Known Activations