© 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. 9-RES-JB
    11. 24295
    Prev
    Next
    INDEX
    Explanations

    concepts related to strengths, weaknesses, and potential value in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    conceptual strengths and weaknesses similar to importance and limitations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Ĥİ
    -0.79
    swick
    -0.79
     batches
    -0.67
    thouse
    -0.64
    Benz
    -0.60
    phalt
    -0.60
    ulp
    -0.59
     INC
    -0.58
    ighth
    -0.57
     Gutierrez
    -0.57
    POSITIVE LOGITS
     comparable
    0.86
     whatsoever
    0.80
     capability
    0.79
     fetish
    0.75
     describ
    0.75
     tendency
    0.75
     resemblance
    0.73
     similar
    0.73
     unlike
    0.73
     knack
    0.73
    Activations Density 0.374%

    No Known Activations