© 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. 2-RES-JB
    11. 17144
    Prev
    Next
    INDEX
    Explanations

    phrases ending with commas and quotes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating pauses or breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.68
    aware
    -0.67
    FIN
    -0.67
    lik
    -0.66
     appra
    -0.64
    escription
    -0.63
    knit
    -0.62
    haus
    -0.62
    eg
    -0.61
    past
    -0.61
    POSITIVE LOGITS
    neau
    0.75
     Flavoring
    0.74
     CCP
    0.70
    netflix
    0.69
     Died
    0.68
    xual
    0.67
    Leary
    0.66
     HSBC
    0.66
     Walters
    0.66
    vasive
    0.65
    Activations Density 0.000%

    No Known Activations