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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10106
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in 'ly'

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and qualifiers in discourse

    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
    "},"
    -0.77
    aily
    -0.67
    /"
    -0.66
    ocaust
    -0.64
    kamp
    -0.63
    kefeller
    -0.61
    addons
    -0.60
    "))
    -0.60
    clock
    -0.59
    ilater
    -0.58
    POSITIVE LOGITS
     speaking
    1.11
    ,
    0.93
    adays
    0.80
     there
    0.72
    speaking
    0.72
    ,.
    0.71
    ,,
    0.71
    !,
    0.70
    ,...
    0.68
     it
    0.66
    Activations Density 0.175%

    No Known Activations