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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5641
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic regions such as counties

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical administrative divisions, particularly counties and villages

    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
    rawdownloadcloneembedreportprint
    -0.69
     agent
    -0.65
     procedure
    -0.64
    PUT
    -0.60
     protocol
    -0.59
     induction
    -0.56
    Journal
    -0.55
    Witness
    -0.55
     Protocol
    -0.54
    OUT
    -0.54
    POSITIVE LOGITS
    hips
    1.38
    chool
    1.16
    folk
    1.08
    hip
    1.00
    poons
    0.99
    hare
    0.93
    pots
    0.89
    aurus
    0.85
    peak
    0.85
     bordering
    0.85
    Activations Density 0.094%

    No Known Activations