© 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. 7-RES-JB
    11. 13512
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific locations or structures with capitalization patterns peculiar to proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    sentences or clauses that conclude thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maiden
    -0.77
     referees
    -0.73
     prol
    -0.72
     worms
    -0.69
     advoc
    -0.69
     aven
    -0.68
     extermin
    -0.67
     additive
    -0.67
     worm
    -0.67
     nearest
    -0.67
    POSITIVE LOGITS
     Photograph
    1.21
     Photo
    1.17
    jpg
    1.12
     Courtesy
    1.06
     Picture
    1.03
     REUTERS
    1.03
     PHOTO
    1.02
     Photographer
    0.98
     Retrieved
    0.97
    Photo
    0.97
    Activations Density 0.325%

    No Known Activations