© 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. 22548
    Prev
    Next
    INDEX
    Explanations

    words containing the specific sequence "ene"

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical compounds or enzymes

    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
    ties
    -0.99
    icago
    -0.81
    things
    -0.73
    THING
    -0.71
    lime
    -0.71
    enegger
    -0.69
    oons
    -0.68
    today
    -0.66
    ricanes
    -0.66
    uitous
    -0.65
    POSITIVE LOGITS
    uve
    1.30
    alogy
    1.28
    volent
    1.15
    agles
    1.10
    utics
    1.04
    utic
    1.02
     Wenger
    0.97
    utical
    0.96
    agle
    0.92
    vol
    0.89
    Activations Density 0.064%

    No Known Activations