© 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. 7006
    Prev
    Next
    INDEX
    Explanations

    violent or aggressive actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to punishment and control

    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
    ItemTracker
    -0.57
    Downloadha
    -0.56
    ãĤ´ãĥ³
    -0.55
    dating
    -0.53
     dotted
    -0.53
    nih
    -0.52
     Nos
    -0.51
     fashioned
    -0.50
    arij
    -0.50
    ebook
    -0.49
    POSITIVE LOGITS
    uate
    0.80
    ISE
    0.63
    enance
    0.62
    ulate
    0.59
     them
    0.58
    itate
    0.58
     him
    0.58
    igate
    0.58
     oneself
    0.55
     RELEASE
    0.55
    Activations Density 0.660%

    No Known Activations