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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24371
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of questions and discussions surrounding uncertainty or clarification

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

    No Comments

    Negative Logits
     <!--
    -0.70
     karma
    -0.66
     merc
    -0.65
     uncommon
    -0.65
     tidy
    -0.63
    "!
    -0.61
     mug
    -0.60
     sans
    -0.59
    ");
    -0.59
     inf
    -0.58
    POSITIVE LOGITS
    yss
    0.93
    Dialogue
    0.81
    laughs
    0.80
    plet
    0.79
    laughter
    0.74
     Transcript
    0.74
    velt
    0.73
     GOODMAN
    0.73
    Secretary
    0.71
     helic
    0.70
    Activations Density 1.100%

    No Known Activations