© 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. 7-RES-JB
    11. 19439
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data organization and analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization and structure in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Origins
    -0.63
     charism
    -0.63
     Identity
    -0.57
    oÄŁ
    -0.53
     Partnership
    -0.51
    Delivery
    -0.51
     Liberation
    -0.49
    Status
    -0.49
     Facts
    -0.49
    Population
    -0.49
    POSITIVE LOGITS
    mith
    1.29
    pace
    1.26
    paces
    1.26
    hips
    1.19
    hip
    1.17
    peed
    1.16
    hift
    1.11
    heet
    1.08
    pring
    1.08
    creen
    1.06
    Activations Density 0.862%

    No Known Activations