© 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. 11-RES-JB
    11. 9910
    Prev
    Next
    INDEX
    Explanations

    names ending in "er" or "ner"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haste
    -0.62
     favour
    -0.60
     electoral
    -0.59
     abolition
    -0.58
     vegetarian
    -0.57
     Filipino
    -0.55
     Gujar
    -0.55
     NULL
    -0.54
     Carbuncle
    -0.54
     fastest
    -0.54
    POSITIVE LOGITS
    stein
    1.44
    idge
    1.32
    lein
    1.29
    geist
    1.23
    lund
    1.22
    wald
    1.21
    baum
    1.20
    hoff
    1.19
    mann
    1.18
    bach
    1.17
    Activations Density 0.205%

    No Known Activations