© 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. 12-RES-JB
    11. 4765
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications and features of equipment or machinery

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    technical terms and concepts related to safety and standards in engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     christ
    -0.81
     skelet
    -0.80
     americ
    -0.78
     republican
    -0.76
     elves
    -0.75
     ethn
    -0.75
     posters
    -0.75
     jerseys
    -0.74
     dreams
    -0.74
     compan
    -0.73
    POSITIVE LOGITS
     Angle
    1.57
     Ratio
    1.53
     Width
    1.47
     Rate
    1.46
     Distance
    1.45
     Delay
    1.43
     Range
    1.43
     Length
    1.41
     Size
    1.41
     Radius
    1.40
    Activations Density 0.335%

    No Known Activations