© 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. 0-RES-JB
    11. 2725
    Prev
    Next
    INDEX
    Explanations

    words related to measurements on a nanometer scale

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "comet" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prejudice
    -0.75
     Stark
    -0.70
     ranger
    -0.69
     title
    -0.65
     trunk
    -0.65
     bark
    -0.64
     summary
    -0.63
     Rhino
    -0.63
     Rampage
    -0.63
     Legacy
    -0.62
    POSITIVE LOGITS
    omet
    4.66
    ometric
    1.72
    imet
    1.55
    ometry
    1.49
    omething
    1.46
    omed
    1.41
    ometers
    1.32
    omes
    1.17
    omew
    1.13
    omen
    1.13
    Activations Density 0.015%

    No Known Activations