© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 991
    Prev
    Next
    INDEX
    Explanations

    io followed by a number, potentially indicating part of a filename or function signature

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "io" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holder
    -0.78
    ivities
    -0.72
    ancies
    -0.71
    puter
    -0.65
    rap
    -0.65
    uates
    -0.65
    selves
    -0.64
    atche
    -0.64
    rier
    -0.61
    INGS
    -0.60
    POSITIVE LOGITS
    ppo
    1.12
    cean
    1.07
    zzi
    1.02
    ctl
    1.01
    ption
    0.96
    ffic
    0.96
    active
    0.91
    vernment
    0.90
    hazard
    0.90
    chi
    0.85
    Activations Density 0.025%

    No Known Activations