© 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. 8054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a superlative or something exceptional

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of the" used in various contexts

    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
    etermination
    -0.62
    ensen
    -0.59
    abad
    -0.59
    oday
    -0.59
    ended
    -0.58
    matter
    -0.57
     aloud
    -0.56
    iture
    -0.56
    ared
    -0.56
     condem
    -0.56
    POSITIVE LOGITS
    few
    0.63
     theirs
    0.62
    chance
    0.62
    dozen
    0.60
    arb
    0.58
     ours
    0.57
     Presidents
    0.57
     continents
    0.57
     those
    0.56
     these
    0.54
    Activations Density 0.087%

    No Known Activations