© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24147
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that involve "if" statements and hypothetical scenarios

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ictionary
    -0.57
    HCR
    -0.54
    GROUND
    -0.53
     groundbreaking
    -0.53
     code
    -0.53
     caution
    -0.52
     thanking
    -0.52
    rocal
    -0.51
    Discussion
    -0.51
     Identification
    -0.51
    POSITIVE LOGITS
     ever
    0.96
     minded
    0.73
     dare
    0.72
    ever
    0.70
    ught
    0.70
     weren
    0.70
     EVER
    0.69
     survive
    0.68
    anium
    0.66
     indeed
    0.66
    Activations Density 0.227%

    No Known Activations