© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23624
    Prev
    Next
    INDEX
    Explanations

    informative or explanatory text, often introduced with phrases like "this is" or "in short"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "this is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.68
    isms
    -0.67
    luaj
    -0.66
    bies
    -0.63
     automakers
    -0.61
    lie
    -0.59
    soever
    -0.59
    shape
    -0.58
     "$:/
    -0.58
     predict
    -0.57
    POSITIVE LOGITS
     NOT
    0.79
     my
    0.74
     definitely
    0.73
     unofficial
    0.72
    claimer
    0.71
     another
    0.70
     an
    0.69
     probably
    0.69
     informative
    0.67
     a
    0.66
    Activations Density 0.104%

    No Known Activations