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. 18262
    Prev
    Next
    INDEX
    Explanations

    words related to technology and programming

    oai_token-act-pair · gpt-3.5-turbo

    verbs and proper nouns that indicate existence or identity

    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
    •EggList

    No Comments

    Negative Logits
     Sally
    -0.72
    touch
    -0.71
    129
    -0.70
    essa
    -0.68
    134
    -0.68
     onion
    -0.67
    secut
    -0.64
    128
    -0.63
     Reese
    -0.62
     ont
    -0.62
    POSITIVE LOGITS
    b
    1.30
    B
    1.20
    Bs
    1.19
    bs
    1.18
    bg
    1.15
    bh
    1.12
    bd
    1.12
    BR
    1.12
    BN
    1.11
    BA
    1.11
    Activations Density 0.332%

    No Known Activations