© 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. 8-RES-JB
    11. 13132
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and correlations between different variables

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding correlations between variables

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Company
    -0.83
    \\\\
    -0.78
    udicrous
    -0.77
     Vaugh
    -0.75
    wered
    -0.75
    ahs
    -0.74
    Ń·
    -0.72
    ufact
    -0.72
    anium
    -0.72
    arna
    -0.72
    POSITIVE LOGITS
     perceptions
    1.22
     propensity
    1.18
     susceptibility
    1.15
     prevalence
    1.12
     outcomes
    1.09
     responses
    1.08
     socioeconomic
    1.08
     attitudes
    1.08
     cognitive
    1.08
     predictive
    1.04
    Activations Density 0.635%

    No Known Activations