© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11532
    Prev
    Next
    INDEX
    Explanations

    information related to quantities or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or measurements of "amount."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.76
    itia
    -0.69
    ATA
    -0.64
    yrs
    -0.63
    kins
    -0.63
     Perspect
    -0.62
    llan
    -0.62
    hett
    -0.60
    stone
    -0.59
    icent
    -0.59
    POSITIVE LOGITS
     amount
    3.71
     amounts
    2.72
    amount
    2.36
     Amount
    2.13
    Amount
    1.92
     quantity
    1.69
     number
    1.62
     quantities
    1.58
     percentage
    1.47
     proportion
    1.44
    Activations Density 0.019%

    No Known Activations