© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 5206
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, especially locations with the term "Blackburn" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or locations, particularly "Blackburn" and "Bolton."

    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
    arist
    -0.85
    ointed
    -0.80
    itia
    -0.79
     skelet
    -0.76
    onym
    -0.76
    utra
    -0.75
    ptic
    -0.69
    ropri
    -0.68
     Ocean
    -0.68
    ggle
    -0.66
    POSITIVE LOGITS
     Blackburn
    1.17
     Bolton
    0.80
    atility
    0.76
    flies
    0.72
     Hew
    0.71
     Sheffield
    0.69
     colours
    0.69
    bugs
    0.67
    atile
    0.66
     Hobby
    0.66
    Activations Density 0.009%

    No Known Activations