© 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. 20732
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas and punctuation, indicating complex sentence structures or separations in thoughts

    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
    rolet
    -0.89
    ROR
    -0.72
    stanbul
    -0.72
    Lenin
    -0.64
    usterity
    -0.64
    ELD
    -0.63
    ISION
    -0.63
     earthqu
    -0.62
    Woman
    -0.61
    aith
    -0.61
    POSITIVE LOGITS
     chances
    1.01
     it
    0.93
     excluding
    0.81
     there
    0.79
     please
    0.79
     minimizing
    0.76
     we
    0.75
     maximizing
    0.75
     determining
    0.74
    many
    0.73
    Activations Density 0.221%

    No Known Activations