© 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. 7-RES-JB
    11. 11381
    Prev
    Next
    INDEX
    Explanations

    phrases related to certainty or comparison

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "as" and related phrases that indicate comparisons or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulner
    -0.72
     ancest
    -0.67
     sway
    -0.57
     unsolved
    -0.56
    inge
    -0.55
    anguages
    -0.54
    mand
    -0.53
    isl
    -0.53
    erto
    -0.53
    hover
    -0.52
    POSITIVE LOGITS
    cow
    0.59
     Cage
    0.57
    reverse
    0.57
    animous
    0.56
    ffield
    0.56
     Oaks
    0.56
    cé
    0.54
    abba
    0.54
    ij士
    0.54
     HELL
    0.54
    Activations Density 0.679%

    No Known Activations