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. 8149
    Prev
    Next
    INDEX
    Explanations

    additional information or actions related to the main topic being discussed

    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
    UGE
    -0.67
     Ange
    -0.62
    click
    -0.62
    AGES
    -0.61
    Exit
    -0.61
    adena
    -0.61
     Dollars
    -0.61
    bound
    -0.60
    renheit
    -0.60
    ASE
    -0.59
    POSITIVE LOGITS
     noted
    0.91
     reportedly
    0.88
     includes
    0.88
     gave
    0.84
     thanked
    0.83
     cautioned
    0.83
     volunteered
    0.82
     benefited
    0.82
     Cosponsors
    0.82
     briefly
    0.82
    Activations Density 0.123%

    No Known Activations