© 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 EvalsExportsAPI 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. 3803
    Prev
    Next
    INDEX
    Explanations

    HTML or coding elements related to specific types of content or advertisements, possibly related to push notifications or gallery interstitials

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and apostrophes, used in dialogue or quotations

    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
    ĻĤ
    -0.77
    robe
    -0.67
    kw
    -0.65
    grounds
    -0.61
     therap
    -0.61
    ensical
    -0.60
    iaries
    -0.60
     Bland
    -0.59
    amily
    -0.59
    rieved
    -0.59
    POSITIVE LOGITS
     meaning
    0.70
     etc
    0.70
     ie
    0.65
     aka
    0.65
    ãĥĥãĤ¯
    0.64
    isu
    0.63
    los
    0.61
    ooters
    0.60
    ushima
    0.60
     although
    0.59
    Activations Density 0.027%

    No Known Activations