© 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. 8-RES-JB
    11. 701
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating a contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    the transition phrases that introduce contrasting information or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLOSE
    -0.62
    anwhile
    -0.59
     Frames
    -0.59
     Flavoring
    -0.57
     Cosmetic
    -0.55
    ufact
    -0.54
    Cause
    -0.53
    idia
    -0.53
     Specifications
    -0.53
    mic
    -0.52
    POSITIVE LOGITS
    ,,
    0.69
    ,
    0.65
    .,
    0.62
     elusive
    0.59
    shapeshifter
    0.58
     stranger
    0.58
    ummer
    0.57
    ALSE
    0.57
    *,
    0.57
    Jere
    0.55
    Activations Density 0.054%

    No Known Activations