Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3179
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or entities, particularly West Bromwich, Ipswich, and individuals with the last name "Halbach."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places, particularly with the suffixes "-wich" or "-lich."

    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
    eworks
    -0.78
    pelling
    -0.68
    hip
    -0.68
    dress
    -0.68
    ynt
    -0.68
    ettes
    -0.67
    natureconservancy
    -0.67
    avorite
    -0.67
    ework
    -0.66
    edes
    -0.66
    POSITIVE LOGITS
    otom
    0.82
    obyl
    0.80
    otomy
    0.78
    wich
    0.78
    ucky
    0.78
    kered
    0.78
    otine
    0.74
    olson
    0.73
    olls
    0.72
    onom
    0.72
    Activations Density 0.075%

    No Known Activations