© 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. 4-RES-JB
    11. 14935
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct quotations and reported speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech or quotations

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

    No Comments

    Negative Logits
    pend
    -0.70
    paralle
    -0.68
    spir
    -0.66
    ortunately
    -0.65
    etheless
    -0.65
    compan
    -0.63
    bent
    -0.62
     broom
    -0.61
    alysed
    -0.61
    fits
    -0.61
    POSITIVE LOGITS
     sarcast
    0.76
     rhet
    0.74
     chuck
    0.68
     bluntly
    0.67
     Superintendent
    0.66
    stals
    0.65
    itud
    0.64
     Trey
    0.62
     Diane
    0.62
     Walters
    0.61
    Activations Density 0.119%

    No Known Activations