© 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. 1-RES-JB
    11. 17341
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly hometowns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "hometown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONS
    -0.88
    assic
    -0.85
    lda
    -0.83
    iasis
    -0.83
    chnology
    -0.75
    err
    -0.75
    abeth
    -0.72
    xual
    -0.70
    agher
    -0.67
    ñ
    -0.66
    POSITIVE LOGITS
     hometown
    0.88
     haunt
    0.76
     favorites
    0.76
     favourite
    0.73
     dwell
    0.73
    sburgh
    0.72
     favourites
    0.71
    scape
    0.69
     neighb
    0.68
     favorite
    0.68
    Activations Density 0.004%

    No Known Activations