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. 4011
    Prev
    Next
    INDEX
    Explanations

    terms related to specific topics or concepts, such as drugs, programming languages, and political figures

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns or proper nouns associated with technology, politics, and culture

    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
    uminati
    -0.73
    akable
    -0.70
    ointed
    -0.70
    20439
    -0.66
    £ı
    -0.65
    ammy
    -0.65
    chest
    -0.62
     Ern
    -0.61
     Plymouth
    -0.60
     Pearce
    -0.57
    POSITIVE LOGITS
     represents
    1.19
     isn
    1.17
     is
    1.16
     tends
    1.12
     exists
    1.11
     lacks
    1.11
     attracts
    1.10
     itself
    1.09
     resembles
    1.08
     differs
    1.06
    Activations Density 0.401%

    No Known Activations