© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 3551
    Prev
    Next
    INDEX
    Explanations

    features related to Q&A sessions

    oai_token-act-pair · gpt-3.5-turbo

    references to Q&A discussions or sessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lit
    -0.91
    gradient
    -0.76
    wcs
    -0.75
    git
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    intendent
    -0.72
    pi
    -0.72
    amina
    -0.71
    nat
    -0.71
    ufact
    -0.70
    POSITIVE LOGITS
     session
    0.87
     interview
    0.76
     guru
    0.76
     interviewer
    0.76
     sessions
    0.75
     Answers
    0.74
    FAQ
    0.70
     Bots
    0.70
     affair
    0.69
     consultations
    0.68
    Activations Density 0.046%

    No Known Activations