© 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. 3-RES-JB
    11. 20770
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "ml" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of milliliters (ml) in the context of measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricular
    -0.81
     Warriors
    -0.72
    nces
    -0.71
    Interstitial
    -0.68
    rex
    -0.66
    Downloadha
    -0.66
    eve
    -0.65
     FANTASY
    -0.63
    DEM
    -0.63
    uliffe
    -0.63
    POSITIVE LOGITS
    vl
    0.94
    ml
    0.91
    inking
    0.90
    ister
    0.89
    anguage
    0.89
    ued
    0.89
    isk
    0.89
    aden
    0.88
    oths
    0.87
    umber
    0.85
    Activations Density 0.014%

    No Known Activations