© 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. 21502
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a specific manner or behavior

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of behavior or actions in a manner that emphasizes their quality and manner of execution

    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
    orsi
    -0.77
     Flavoring
    -0.69
    reon
    -0.67
    utherford
    -0.65
    EEP
    -0.65
    azine
    -0.64
    itters
    -0.64
    reb
    -0.64
    irin
    -0.64
    bledon
    -0.64
    POSITIVE LOGITS
     manner
    2.03
     way
    1.79
     fashion
    1.78
     ways
    1.48
     manners
    1.26
     WAY
    1.24
    fashion
    1.19
     vein
    1.12
     guise
    1.08
     Way
    1.04
    Activations Density 0.217%

    No Known Activations