Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 317
    Prev
    Next
    INDEX
    Explanations

    words related to political and economic discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    283
    +0.12
    0.5%
    582
    +0.11
    0.5%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.11
    343
    +0.11
    0.09
    314
    +0.10
    0.01
    Negative Logits
     Gutenberg
    -0.64
     essence
    -0.61
     dere
    -0.59
     Nadu
    -0.58
    pora
    -0.57
     Hoo
    -0.56
     Ceres
    -0.56
    coni
    -0.55
     por
    -0.55
    bilt
    -0.55
    POSITIVE LOGITS
    odies
    1.38
    amboo
    1.19
    ibli
    1.17
    rief
    1.16
    rows
    1.15
    ruary
    1.11
    asket
    1.10
    isexual
    1.07
    ishops
    1.07
    acteria
    1.05
    Activations Density 2.814%

    No Known Activations