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. 8-RES-JB
    6. 19745
    Prev
    Next
    INDEX
    Explanations

    terms related to specific professions or activities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to sports, particularly baseball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conc
    -0.70
     Honour
    -0.68
    Link
    -0.64
     Peer
    -0.63
    ĪĴ
    -0.62
     Strauss
    -0.61
     Judicial
    -0.59
     Revel
    -0.59
    Gar
    -0.59
     Millenn
    -0.58
    POSITIVE LOGITS
     (%
    0.68
    ollah
    0.67
    gage
    0.60
    species
    0.59
    ace
    0.59
    reb
    0.59
     Jinping
    0.59
     âĶľâĶĢâĶĢ
    0.57
    EStream
    0.56
    ache
    0.55
    Activations Density 0.148%

    No Known Activations