© 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. 4-RES-JB
    11. 12327
    Prev
    Next
    INDEX
    Explanations

    names, places, and terms related to a caravan

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups, particularly with the name "avan."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     reluct
    -0.85
    ĨĴ
    -0.84
     mathemat
    -0.83
     conduc
    -0.80
     suspic
    -0.78
    omething
    -0.77
     predictive
    -0.77
     corros
    -0.76
     nomine
    -0.75
     commenter
    -0.71
    POSITIVE LOGITS
    agh
    1.24
    avan
    1.21
    ese
    0.90
    ahu
    0.82
    abal
    0.82
    arta
    0.80
    athan
    0.80
    icz
    0.80
    adium
    0.79
    aban
    0.77
    Activations Density 0.015%

    No Known Activations