© 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 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. 9-RES-JB
    11. 2313
    Prev
    Next
    INDEX
    Explanations

    phrases or terms referring to previous instances or historical context

    oai_token-act-pair · gpt-3.5-turbo

    references to prior content or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.81
    bucks
    -0.75
     Franch
    -0.74
     Himself
    -0.72
    abad
    -0.72
    pter
    -0.71
    atown
    -0.70
    alion
    -0.70
    icles
    -0.70
    csv
    -0.68
    POSITIVE LOGITS
     generations
    1.26
     incarnation
    1.19
     incarn
    1.12
     iterations
    1.12
    ebin
    1.11
     administrations
    1.10
     editions
    1.08
     eras
    1.07
     installments
    1.06
     iteration
    1.02
    Activations Density 0.059%

    No Known Activations