© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 22342
    Prev
    Next
    INDEX
    Explanations

    superlatives like "oldest," "fastest," and "shortest."

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives that indicate extremes or best qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tis
    -0.74
    yang
    -0.72
    olor
    -0.71
    umat
    -0.70
    ending
    -0.69
    align
    -0.69
    yi
    -0.68
    rompt
    -0.66
    icing
    -0.66
    alus
    -0.65
    POSITIVE LOGITS
     conceivable
    1.33
     imaginable
    1.31
     possible
    1.26
     ever
    1.08
     practicable
    1.03
     thing
    0.96
     extant
    0.90
     EVER
    0.87
     feasible
    0.81
     surviving
    0.79
    Activations Density 0.070%

    No Known Activations