© 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. 12940
    Prev
    Next
    INDEX
    Explanations

    unstructured text and random numerical values, potentially related to coding or data

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values or statistics within the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     spitting
    -0.84
     barr
    -0.83
     communicating
    -0.78
     building
    -0.78
     spir
    -0.77
     frontline
    -0.76
     regener
    -0.76
     mutually
    -0.75
     hypot
    -0.74
     flaming
    -0.74
    POSITIVE LOGITS
    RAW
    1.85
    Rated
    1.82
    âĵĺ
    1.68
    Loading
    1.60
    Topic
    1.60
    Reviewer
    1.59
    Topics
    1.57
    Advertisements
    1.55
    Advertisement
    1.54
    Contents
    1.51
    Activations Density 0.303%

    No Known Activations