© 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. 6-RES-JB
    11. 5575
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Do"

    oai_token-act-pair · gpt-3.5-turbo

    questions posed to the reader

    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
    Reviewer
    -0.83
    )=(
    -0.70
    boarding
    -0.70
    workshop
    -0.69
    creen
    -0.67
    Software
    -0.65
    cream
    -0.64
     Azerb
    -0.63
     Handling
    -0.63
    EStreamFrame
    -0.62
    POSITIVE LOGITS
    omsday
    1.34
    ppel
    1.18
    herty
    1.12
    zens
    1.06
    lez
    1.05
    lyak
    0.98
    oley
    0.95
    ozy
    0.91
    ggies
    0.90
    oway
    0.90
    Activations Density 0.081%

    No Known Activations