© 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. 1-RES-JB
    11. 7499
    Prev
    Next
    INDEX
    Explanations

    mentions of things being significant or important

    oai_token-act-pair · gpt-3.5-turbo

    the term "big" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inel
    -0.80
    manship
    -0.77
    DragonMagazine
    -0.75
    AUT
    -0.74
    clair
    -0.73
    cia
    -0.73
    cius
    -0.71
    voy
    -0.70
    chron
    -0.70
    Discover
    -0.69
    POSITIVE LOGITS
    gest
    1.01
    oted
    0.93
     chunk
    0.91
    GER
    0.87
     bang
    0.82
     ol
    0.78
     payday
    0.77
     bulky
    0.75
     deal
    0.74
     hairy
    0.74
    Activations Density 0.031%

    No Known Activations