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. 7-RES-JB
    6. 22527
    Prev
    Next
    INDEX
    Explanations

    mentions of the geographic location "Sierra"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sierra or locations specifically associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sworth
    -0.82
    umbn
    -0.69
    esty
    -0.68
    SHIP
    -0.67
    rontal
    -0.67
    orate
    -0.66
    purpose
    -0.65
    spring
    -0.64
    ueller
    -0.64
    oppable
    -0.64
    POSITIVE LOGITS
     Leone
    1.44
     Nevada
    0.95
     Alto
    0.93
     Scotia
    0.81
     Designs
    0.80
    BIL
    0.77
    ierra
    0.76
     Vista
    0.76
    illo
    0.75
     Isles
    0.74
    Activations Density 0.017%

    No Known Activations