© 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. 7-RES-JB
    11. 1869
    Prev
    Next
    INDEX
    Explanations

    mentions of people involved in negative or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in crime-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecause
    -0.75
    raltar
    -0.72
    cale
    -0.69
    aeda
    -0.67
    olesterol
    -0.62
    ilaterally
    -0.61
    OME
    -0.60
    Est
    -0.60
    agascar
    -0.59
    forestation
    -0.59
    POSITIVE LOGITS
    's
    0.83
     testified
    0.81
     thanked
    0.77
     pleaded
    0.75
    nels
    0.75
     surn
    0.74
     wore
    0.74
     withdrew
    0.74
     went
    0.73
     lied
    0.73
    Activations Density 0.261%

    No Known Activations