© 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. 5085
    Prev
    Next
    INDEX
    Explanations

    descriptions of scenes or moments in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    elements related to significant moments or concepts in narratives

    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
    eworthy
    -0.68
     Pry
    -0.66
    orthy
    -0.66
    dx
    -0.66
    pter
    -0.66
    racuse
    -0.64
    CAST
    -0.63
     repro
    -0.63
     TY
    -0.63
     Helpful
    -0.63
    POSITIVE LOGITS
     alone
    0.78
    é¾įå¥ij士
    0.69
    ativity
    0.67
     haun
    0.65
    ioned
    0.65
    ieri
    0.64
    milo
    0.64
     Ronaldo
    0.63
    eto
    0.62
    ange
    0.62
    Activations Density 0.274%

    No Known Activations