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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6955
    Prev
    Next
    INDEX
    Explanations

    numeric values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with finance and contracts

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

    No Comments

    Negative Logits
    wart
    -0.77
    ways
    -0.76
    egal
    -0.73
    shire
    -0.70
    warts
    -0.67
    atic
    -0.67
    open
    -0.67
    elong
    -0.66
    alg
    -0.65
    sterdam
    -0.64
    POSITIVE LOGITS
    cffff
    0.78
     needles
    0.67
    issance
    0.66
     pes
    0.63
     MHz
    0.63
    NESS
    0.62
    rious
    0.62
    PDATE
    0.62
     calories
    0.62
    MENTS
    0.62
    Activations Density 0.054%

    No Known Activations