© 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. 9-RES-JB
    11. 18621
    Prev
    Next
    INDEX
    Explanations

    conditional statements with a cause-effect relationship

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements that imply a contrast or challenge to a preceding assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pec
    -0.72
    olitical
    -0.70
    VERTISEMENT
    -0.68
    ouble
    -0.67
    oked
    -0.66
    nai
    -0.66
    apsed
    -0.66
    resent
    -0.64
    ThumbnailImage
    -0.64
    minster
    -0.64
    POSITIVE LOGITS
     then
    1.31
    then
    1.29
     surely
    1.12
     why
    1.10
     chances
    1.04
     THEN
    1.04
     congratulations
    0.96
     please
    0.91
     maybe
    0.88
     it
    0.87
    Activations Density 0.220%

    No Known Activations