© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9555
    Prev
    Next
    INDEX
    Explanations

    instances of contrasting information or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTE
    -0.73
    ENGTH
    -0.62
    ILLE
    -0.61
    BILITY
    -0.59
    inger
    -0.58
    rus
    -0.56
    IRT
    -0.54
    USS
    -0.54
    rology
    -0.54
    rower
    -0.54
    POSITIVE LOGITS
     but
    2.45
    but
    2.16
     BUT
    1.80
     But
    1.43
    But
    1.41
    BUT
    1.30
     although
    1.27
    though
    1.23
     except
    1.22
     albeit
    1.19
    Activations Density 0.157%

    No Known Activations