© 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. 24069
    Prev
    Next
    INDEX
    Explanations

    the word "a" followed by a word starting with a vowel sound

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'a.'

    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
     Allied
    -0.75
     intended
    -0.74
     events
    -0.69
     Oswald
    -0.68
     Operation
    -0.67
     Agg
    -0.67
     Anchorage
    -0.65
     urgent
    -0.63
     ALP
    -0.63
     Avalanche
    -0.62
    POSITIVE LOGITS
    pron
    1.27
    uras
    1.22
    ero
    1.20
    esthetic
    1.20
    ural
    1.18
    ird
    1.18
    unts
    1.17
    sembly
    1.17
    lex
    1.17
    eon
    1.16
    Activations Density 0.133%

    No Known Activations