© 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. 2-RES-JB
    11. 12707
    Prev
    Next
    INDEX
    Explanations

    the word "However" to indicate a contrasting or contradictory statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However" signaling contrast or transition in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '),
    -0.60
    uto
    -0.59
    isable
    -0.58
    esses
    -0.57
    endered
    -0.57
    ').
    -0.57
    enders
    -0.57
     cattle
    -0.56
     é
    -0.56
    advertising
    -0.56
    POSITIVE LOGITS
     interestingly
    0.77
    CLASSIFIED
    0.77
    theless
    0.73
     importantly
    0.70
     fortunately
    0.67
     unden
    0.66
    tons
    0.65
     Err
    0.64
    THER
    0.64
    ALSE
    0.62
    Activations Density 0.024%

    No Known Activations