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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22161
    Prev
    Next
    INDEX
    Explanations

    mentions of specific towns or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "town."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    positive
    -0.73
    wcsstore
    -0.73
    uberty
    -0.69
    utic
    -0.68
    xual
    -0.67
    fen
    -0.67
    olitics
    -0.65
    uchin
    -0.65
    zek
    -0.65
    Wan
    -0.64
    POSITIVE LOGITS
    folk
    1.21
    houses
    1.12
    spe
    1.10
     halls
    1.01
     hall
    1.00
    house
    0.99
    ships
    0.94
    rooms
    0.93
    scape
    0.90
    area
    0.87
    Activations Density 0.031%

    No Known Activations