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. 7-RES-JB
    6. 8238
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers with a hyphen or slash following the number

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and formatting that signify sentence boundaries

    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
     Rally
    -0.66
     Colossus
    -0.65
     Squadron
    -0.65
     presc
    -0.64
    oche
    -0.62
     Classics
    -0.62
     Hail
    -0.62
     Transition
    -0.61
     scrap
    -0.61
     GP
    -0.60
    POSITIVE LOGITS
    ³³³
    1.08
    ³³³³
    1.00
    ³³³³³³³³
    1.00
    ↵Âł
    1.00
     Âł
    0.99
    ³³
    0.97
     Âł Âł Âł Âł
    0.90
     Âł Âł
    0.90
     ³³
    0.89
    ³³³³³³³³³³³³³³³³
    0.89
    Activations Density 0.513%

    No Known Activations