© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2413
    Prev
    Next
    INDEX
    Explanations

    locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods indicating sentence endings

    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
     extinct
    -1.01
     pudding
    -0.77
     regenerate
    -0.75
     councils
    -0.74
     microbiome
    -0.74
     compens
    -0.73
     recons
    -0.73
     ditch
    -0.71
     affili
    -0.71
     cripp
    -0.70
    POSITIVE LOGITS
     During
    1.17
     Afterwards
    1.13
     Located
    1.11
     Upon
    1.10
     Along
    1.09
     They
    1.09
     Sitting
    1.07
     Moments
    1.04
     He
    1.03
     Initially
    1.03
    Activations Density 0.369%

    No Known Activations