© 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. 3-RES-JB
    11. 14765
    Prev
    Next
    INDEX
    Explanations

    words related to a specific geographical location (Montana)

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Montana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uers
    -0.85
    atics
    -0.82
    rers
    -0.74
    inse
    -0.74
    pled
    -0.73
    ophen
    -0.71
    visual
    -0.70
    rupulous
    -0.69
    ear
    -0.69
    seller
    -0.68
    POSITIVE LOGITS
     Montana
    1.16
     Grizzlies
    0.96
     Falls
    0.81
     Firearms
    0.77
     Nebraska
    0.75
    adelphia
    0.73
     Lob
    0.73
    aign
    0.72
    sylvania
    0.71
     Wyoming
    0.71
    Activations Density 0.006%

    No Known Activations