© 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. 5093
    Prev
    Next
    INDEX
    Explanations

    It looks for statements indicating knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    statements of knowledge or factual assertions

    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
    pex
    -0.87
    oshenko
    -0.75
    cit
    -0.73
    cific
    -0.67
    cohol
    -0.65
    otti
    -0.65
    cus
    -0.65
    ksh
    -0.64
    onies
    -0.64
    rentice
    -0.64
    POSITIVE LOGITS
     ourselves
    0.85
     how
    0.73
    ledge
    0.71
    ledged
    0.71
     plenty
    0.71
    ariat
    0.68
     hinges
    0.66
    lege
    0.62
     enough
    0.62
     nothing
    0.62
    Activations Density 0.090%

    No Known Activations