© 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. 5078
    Prev
    Next
    INDEX
    Explanations

    references to sightings or observations of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seen."

    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
    angan
    -0.73
    mental
    -0.71
    idity
    -0.70
    sett
    -0.68
    otomy
    -0.64
     assignment
    -0.63
    cussion
    -0.62
     anthem
    -0.61
     spinal
    -0.60
    aceutical
    -0.60
    POSITIVE LOGITS
    IOR
    0.86
    ById
    0.85
    wcsstore
    0.82
    IRT
    0.81
    swick
    0.80
    hao
    0.77
    dust
    0.75
    seeing
    0.72
    Ĺ
    0.71
    PsyNetMessage
    0.71
    Activations Density 0.036%

    No Known Activations