© 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. 9-RES-JB
    11. 4131
    Prev
    Next
    INDEX
    Explanations

    numerical strings and technical codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values mixed with code-like structures

    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
     passionate
    -0.61
     sponsor
    -0.58
     roadside
    -0.57
     announcement
    -0.57
     demand
    -0.57
     caution
    -0.57
     trimmed
    -0.56
     safeguards
    -0.56
     mathemat
    -0.56
     gam
    -0.56
    POSITIVE LOGITS
    uchi
    0.88
    sac
    0.86
    tx
    0.81
    pta
    0.81
    rage
    0.80
    oops
    0.80
    fu
    0.79
    uminium
    0.78
    eri
    0.78
    shapeshifter
    0.77
    Activations Density 0.216%

    No Known Activations