© 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. 4160
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms and their definitions or implications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categorization or classification concepts

    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
     immensely
    -0.67
    nces
    -0.64
    etheless
    -0.62
     tremendously
    -0.60
     hugely
    -0.59
     truthful
    -0.58
     wonderful
    -0.58
    encies
    -0.57
     unimaginable
    -0.56
     wonderfully
    -0.56
    POSITIVE LOGITS
    "—
    0.83
     syndrome
    0.74
    ".
    0.74
     Syndrome
    0.72
    ",
    0.72
    "?
    0.70
    "
    0.68
    interstitial
    0.68
    ":
    0.68
     versus
    0.67
    Activations Density 0.391%

    No Known Activations