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. 21618
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology, particularly related to cryptocurrencies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or titles of individuals

    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
     Rebels
    -0.66
     Bray
    -0.65
     saline
    -0.65
     Scotia
    -0.64
     trooper
    -0.63
     Bundy
    -0.62
     sexes
    -0.62
     Ceres
    -0.61
     Solitaire
    -0.60
     Maced
    -0.60
    POSITIVE LOGITS
    amoto
    1.61
    azaki
    1.48
    imura
    1.42
    amura
    1.30
    asaki
    1.26
    amaru
    1.25
    ihara
    1.23
    ikawa
    1.18
    oka
    1.14
    akura
    1.13
    Activations Density 0.059%

    No Known Activations