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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41340
    Prev
    Next
    INDEX
    Explanations

    discussions regarding race and intelligence and their connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.35
    1.9%
    481
    +0.12
    0.6%
    367
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.35
    -0.01
    367
    +0.12
    0.08
    561
    +0.10
    0.06
    Negative Logits
     UNCLASSIFIED
    -0.83
    anwhile
    -0.72
    theless
    -0.70
     [*
    -0.68
     pse
    -0.67
     Azerb
    -0.65
    _.
    -0.65
    ogether
    -0.64
     encour
    -0.64
    etheless
    -0.63
    POSITIVE LOGITS
     âĢº
    0.82
     Belfast
    0.75
     Donald
    0.73
     âĢİ
    0.62
     Updated
    0.61
     Hillary
    0.61
     Hearthstone
    0.60
     Posted
    0.59
     cryptocurrency
    0.59
     LEGO
    0.59
    Activations Density 1.360%

    No Known Activations