© 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. 19973
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and variations of the phrase "before" to denote sequences or conditions in statements

    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
    advertisement
    -0.78
    cffffcc
    -0.71
    áµ
    -0.68
     teasp
    -0.67
     Himself
    -0.63
    ãĤ´ãĥ³
    -0.61
    fine
    -0.61
    fit
    -0.61
    puff
    -0.60
    redit
    -0.60
    POSITIVE LOGITS
     hostilities
    0.86
     we
    0.77
     someone
    0.74
     things
    0.74
     tensions
    0.72
     anyone
    0.71
     humanity
    0.68
     somebody
    0.67
     suspicions
    0.66
     Americans
    0.66
    Activations Density 0.192%

    No Known Activations