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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3337
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically in the Northwestern region

    oai_token-act-pair · gpt-3.5-turbo

    references to the Northwest region

    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
    cher
    -0.71
    OTH
    -0.70
     Hitler
    -0.68
    ========
    -0.68
    idates
    -0.66
    chers
    -0.65
    hement
    -0.65
    TABLE
    -0.65
    uation
    -0.64
    LET
    -0.64
    POSITIVE LOGITS
     Northwest
    1.17
     Territories
    1.12
     Passage
    1.10
     Airlines
    0.99
     Coast
    0.90
     Scotia
    0.89
     Territory
    0.83
     Northeast
    0.81
     Siber
    0.80
     Fisheries
    0.80
    Activations Density 0.008%

    No Known Activations