© 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. 8-RES-JB
    11. 17775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating commonality or similarity between different entities

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in common."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lynn
    -0.72
    Invalid
    -0.71
    ALSE
    -0.67
    Crash
    -0.65
    hov
    -0.62
    OTH
    -0.61
    ilst
    -0.60
    ghan
    -0.59
     ALSO
    -0.57
    llan
    -0.56
    POSITIVE LOGITS
    clusions
    1.12
    organic
    1.03
    roads
    1.00
    effic
    0.99
    between
    0.96
     regards
    0.95
     vitro
    0.95
    animate
    0.94
     relation
    0.91
    ordinate
    0.91
    Activations Density 0.206%

    No Known Activations