© 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. 9168
    Prev
    Next
    INDEX
    Explanations

    instances of personal identification or labeling

    oai_token-act-pair · gpt-3.5-turbo

    references to identification and self-identification

    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
    advertising
    -0.76
    beans
    -0.73
    times
    -0.72
     wraps
    -0.72
    env
    -0.71
    issance
    -0.69
     prosper
    -0.66
     mull
    -0.66
    cour
    -0.65
     recons
    -0.65
    POSITIVE LOGITS
     culprit
    0.82
    ById
    0.76
     suspects
    0.74
     perpetrator
    0.73
     Location
    0.72
     identifiable
    0.71
     Species
    0.71
     Cosponsors
    0.70
     Incident
    0.69
     Individuals
    0.69
    Activations Density 0.263%

    No Known Activations