© 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. 961
    Prev
    Next
    INDEX
    Explanations

    specifically named authors in academic paper citations

    oai_token-act-pair · gpt-3.5-turbo

    references to authors or collaborators in cited academic work

    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
    OUNT
    -0.78
    canon
    -0.75
    FUL
    -0.73
    esses
    -0.73
    rontal
    -0.69
    OWS
    -0.67
    Meat
    -0.66
    ACP
    -0.63
    ardless
    -0.63
    IFT
    -0.61
    POSITIVE LOGITS
     seq
    1.21
    rics
    0.92
     al
    0.89
    ween
    0.82
    sis
    0.81
    ree
    0.81
    hetically
    0.80
     Associates
    0.74
    lace
    0.74
    iated
    0.73
    Activations Density 0.011%

    No Known Activations