© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6832
    Prev
    Next
    INDEX
    Explanations

    the word "but" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" and its variations, indicating contrasts or exceptions

    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
    roy
    -0.69
    million
    -0.68
     segment
    -0.67
    Tube
    -0.65
    esc
    -0.64
    entry
    -0.63
    tnc
    -0.62
    uto
    -0.62
    Times
    -0.61
    ump
    -0.60
    POSITIVE LOGITS
     alas
    1.10
     nevertheless
    1.10
     nonetheless
    1.06
    tons
    1.04
     luckily
    1.02
     fortunately
    0.96
    chery
    0.95
     hey
    0.94
     unfortunately
    0.83
     thankfully
    0.82
    Activations Density 0.223%

    No Known Activations