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. 12037
    Prev
    Next
    INDEX
    Explanations

    numeric and technical terms, as well as references to television programs and other media

    oai_token-act-pair · gpt-3.5-turbo

    instances of text that indicate the end of a document or section

    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
    .")
    -0.70
     worrying
    -0.67
     ÂŃ
    -0.64
     surrog
    -0.63
     showc
    -0.62
    â̦."
    -0.61
    â̦]
    -0.60
    advertisement
    -0.60
     withd
    -0.60
    ··
    -0.60
    POSITIVE LOGITS
     âĵĺ
    0.81
    Joined
    0.76
     Description
    0.68
     Daughter
    0.64
     Died
    0.64
    ometown
    0.64
     ENG
    0.62
     Location
    0.62
     Located
    0.62
     1280
    0.61
    Activations Density 0.681%

    No Known Activations