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. 3-RES-JB
    6. 21561
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the Sierra region

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sierra," particularly in geographical or location contexts

    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
    secondary
    -0.75
    umbn
    -0.73
    ifier
    -0.72
    raped
    -0.72
    animous
    -0.71
    roit
    -0.70
    SHIP
    -0.70
    relations
    -0.69
    rontal
    -0.67
    estate
    -0.66
    POSITIVE LOGITS
     Leone
    1.23
     Sierra
    1.00
    ierra
    0.98
     Nevada
    0.95
     Alto
    0.94
     Vista
    0.89
     Designs
    0.88
     Scotia
    0.79
    BIL
    0.76
     Achievement
    0.75
    Activations Density 0.003%

    No Known Activations