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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8537
    Prev
    Next
    INDEX
    Explanations

    locations, particularly in the New York area

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and associated names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounter
    -0.68
     nonetheless
    -0.60
    uer
    -0.58
    DER
    -0.58
    rawdownloadcloneembedreportprint
    -0.57
    nc
    -0.57
    ibur
    -0.57
    wikipedia
    -0.56
    oteric
    -0.56
     IPM
    -0.55
    POSITIVE LOGITS
     Aires
    0.86
     Island
    0.83
    adelphia
    0.82
    ĩ
    0.80
     Islanders
    0.80
    ī
    0.77
     Rica
    0.77
    burgh
    0.76
    ãĥİ
    0.74
    phia
    0.74
    Activations Density 0.137%

    No Known Activations