© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17019
    Prev
    Next
    INDEX
    Explanations

    mentions of specific magazine issues

    oai_token-act-pair · gpt-3.5-turbo

    references to specific magazine issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.83
    berman
    -0.78
    eric
    -0.77
    oggles
    -0.76
    tsky
    -0.76
    bones
    -0.75
    bsite
    -0.74
    oga
    -0.74
    ãĤī
    -0.72
    sle
    -0.70
    POSITIVE LOGITS
    DonaldTrump
    0.80
     Comics
    0.80
     Issue
    0.71
     1850
    0.69
     reel
    0.66
     Valiant
    0.65
     1897
    0.65
     issue
    0.64
    Issue
    0.62
    agents
    0.62
    Activations Density 0.024%

    No Known Activations