© 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. 18772
    Prev
    Next
    INDEX
    Explanations

    keywords related to ventilation or breathing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vent" and its variations

    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
     Hitman
    -0.75
    makers
    -0.70
    making
    -0.69
     Kerry
    -0.68
    maker
    -0.66
    lihood
    -0.64
    ×Ķ
    -0.61
     Hath
    -0.60
     Lennon
    -0.59
     phosphate
    -0.56
    POSITIVE LOGITS
    ricular
    1.60
    ilated
    1.52
    ilation
    1.39
    urous
    1.34
    uring
    1.28
    ral
    1.22
    rue
    1.17
    uri
    1.13
    raint
    1.12
    urers
    1.08
    Activations Density 0.049%

    No Known Activations