© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases indicating a range or a comparison

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases indicating quantifiable metrics or significant changes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Polo
    -0.77
     Compass
    -0.74
     composition
    -0.74
     Definition
    -0.72
     Mechdragon
    -0.71
     chairs
    -0.70
     Samp
    -0.67
     resolution
    -0.67
     generation
    -0.66
     Swordsman
    -0.66
    POSITIVE LOGITS
    needed
    1.60
    anticipated
    1.56
    awaited
    1.44
    mal
    1.40
    hyp
    1.39
    talk
    1.34
    crit
    1.29
    trump
    1.27
    request
    1.25
    advert
    1.18
    Activations Density 0.051%

    No Known Activations