© 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. 4656
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical attributes or conditions, especially those involving moisture or medical implications

    oai_token-act-pair · gpt-3.5-turbo

    references to events or situations involving meteorites and environmental interactions

    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
     :=
    -0.82
    igi
    -0.71
    antage
    -0.69
    emale
    -0.68
    ftime
    -0.67
    ctors
    -0.63
    ggles
    -0.63
    every
    -0.61
     Equality
    -0.61
    ishops
    -0.61
    POSITIVE LOGITS
     prank
    0.79
     nefarious
    0.78
     somewhere
    0.77
     explosives
    0.76
     somew
    0.75
     improperly
    0.74
    nikov
    0.73
     improper
    0.72
     smugglers
    0.71
     undet
    0.71
    Activations Density 1.028%

    No Known Activations