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

    Neuronpedia

    APICircuit 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. 9304
    Prev
    Next
    INDEX
    Explanations

    mentions of rain or related weather conditions

    oai_token-act-pair · gpt-3.5-turbo
    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
    entric
    -0.82
    ó
    -0.77
    ovo
    -0.76
    ancial
    -0.71
    lde
    -0.69
    atown
    -0.69
    VICE
    -0.68
    ernel
    -0.66
    ounter
    -0.65
     Cosponsors
    -0.65
    POSITIVE LOGITS
    bows
    1.77
    forest
    1.48
    drops
    1.46
    water
    1.21
    storms
    1.18
    bow
    1.18
    drop
    1.14
    storm
    1.13
    meter
    1.10
    coat
    1.09
    Activations Density 0.034%

    No Known Activations