© 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. 4-RES-JB
    11. 4291
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a comparison or evaluation of different things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the phrase "in terms of."

    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
    ards
    -0.74
    iste
    -0.72
    iologist
    -0.71
    iens
    -0.70
    ANS
    -0.70
    iland
    -0.69
    isite
    -0.68
    ©¶æ¥µ
    -0.68
    arette
    -0.67
    itions
    -0.64
    POSITIVE LOGITS
     chronological
    0.80
     precaution
    0.77
     sheer
    0.72
     totality
    0.71
     convenience
    0.71
     legality
    0.70
     preserving
    0.68
     travel
    0.66
     geography
    0.65
     transferring
    0.65
    Activations Density 0.049%

    No Known Activations