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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5185
    Prev
    Next
    INDEX
    Explanations

    numerical figures related to quantities, measurements, or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values in the format of large numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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

    Negative Logits
    ifice
    -0.67
    venge
    -0.67
    otto
    -0.64
    rival
    -0.64
    krit
    -0.64
    iqu
    -0.63
    ufact
    -0.61
     weakened
    -0.61
    ivity
    -0.61
    nam
    -0.60
    POSITIVE LOGITS
    +
    1.09
    Hz
    1.07
    mAh
    0.95
    bps
    0.95
     lbs
    0.93
     crore
    0.92
    lbs
    0.90
     Hz
    0.90
    ths
    0.89
    lb
    0.89
    Activations Density 0.087%

    No Known Activations