© 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. 20810
    Prev
    Next
    INDEX
    Explanations

    common verbs related to police or investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "found" related to discoveries or recoveries in various contexts

    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
     privile
    -0.78
    idium
    -0.73
    IQ
    -0.69
    inion
    -0.69
    ename
    -0.68
     paced
    -0.68
     matchup
    -0.67
     horm
    -0.67
    quote
    -0.66
    creation
    -0.66
    POSITIVE LOGITS
     traces
    0.75
    EMS
    0.75
    usky
    0.71
    éļ
    0.70
    dylib
    0.70
     footprints
    0.68
    ered
    0.68
     swast
    0.68
     clues
    0.67
     him
    0.67
    Activations Density 0.061%

    No Known Activations