© 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. 10-RES-JB
    11. 6705
    Prev
    Next
    INDEX
    Explanations

    characters and symbols related to coding and tech environments

    oai_token-act-pair · gpt-3.5-turbo

    negative indicators or error codes in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emmy
    -0.85
     Hag
    -0.73
     emitting
    -0.69
     Anita
    -0.69
     Yen
    -0.69
     Thrones
    -0.69
     Eve
    -0.69
     Giles
    -0.68
     Faith
    -0.67
     Fir
    -0.66
    POSITIVE LOGITS
    tools
    1.53
    utils
    1.44
    modules
    1.44
    setup
    1.42
    cli
    1.42
    mode
    1.38
    generic
    1.31
    server
    1.29
    desktop
    1.29
    wrapper
    1.28
    Activations Density 0.070%

    No Known Activations