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. 20366
    Prev
    Next
    INDEX
    Explanations

    statements related to permissions or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    sequences of text that are empty or contain no relevant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Vaugh
    -0.67
     Niet
    -0.66
     Godd
    -0.64
     Byr
    -0.64
     Brus
    -0.63
     Bravo
    -0.62
    esides
    -0.61
     Strauss
    -0.61
     Gaw
    -0.60
     Barney
    -0.59
    POSITIVE LOGITS
    ¶
    0.78
     optionally
    0.72
     embodiments
    0.67
     specified
    0.67
     ][
    0.67
     interval
    0.66
     integer
    0.65
    obyl
    0.64
     dynamically
    0.64
    ersive
    0.64
    Activations Density 0.737%

    No Known Activations