© 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. 11-RES-JB
    11. 12930
    Prev
    Next
    INDEX
    Explanations

    commands or directives in text

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or recommendations related to improvement or processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    due
    -0.70
     cannot
    -0.55
     Gleaming
    -0.55
     Highlights
    -0.54
     Due
    -0.52
     regards
    -0.51
     signifies
    -0.49
     accuses
    -0.49
    quartered
    -0.48
    nor
    -0.48
    POSITIVE LOGITS
     yourself
    1.36
     instead
    1.30
     yourselves
    1.21
     ourselves
    1.20
     manually
    1.19
     Yourself
    1.15
     beforehand
    1.12
    instead
    1.06
     oneself
    1.06
     altogether
    1.02
    Activations Density 0.720%

    No Known Activations