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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 4576
    Prev
    Next
    INDEX
    Explanations

    directions or instructions for a do-it-yourself (DIY) project

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    369
    +0.10
    0.5%
    342
    +0.10
    0.4%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.10
    0.07
    764
    +0.10
    0.06
    654
    +0.10
    0.06
    Negative Logits
    YP
    -0.78
    ItemThumbnailImage
    -0.74
    LLOW
    -0.70
    Few
    -0.70
    zens
    -0.70
    PRESS
    -0.69
    APH
    -0.69
    ORTS
    -0.67
    Ur
    -0.66
    Bey
    -0.66
    POSITIVE LOGITS
     top
    0.87
     unsuspecting
    0.82
     underside
    0.82
     roofs
    0.79
     bushes
    0.78
    top
    0.78
     cardboard
    0.77
     asphalt
    0.76
     pavement
    0.75
     holes
    0.75
    Activations Density 0.743%

    No Known Activations