© 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. 1543
    Prev
    Next
    INDEX
    Explanations

    references to modified versions of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to modifications or alterations

    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
    çĦ
    -0.83
    ä
    -0.72
    vor
    -0.70
    OPA
    -0.69
    travel
    -0.69
    Mah
    -0.67
    pt
    -0.67
    unts
    -0.66
    line
    -0.66
    tri
    -0.65
    POSITIVE LOGITS
    atile
    0.94
     organisms
    0.79
     modifications
    0.77
     wrench
    0.76
     mitigation
    0.76
     organism
    0.75
     versions
    0.75
    iations
    0.75
     modification
    0.74
    xual
    0.73
    Activations Density 0.017%

    No Known Activations