© 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. 3-RES-JB
    11. 15040
    Prev
    Next
    INDEX
    Explanations

    special abbreviations or acronyms like "SI" and "CSI"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the publication "Sports Illustrated" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    busters
    -0.76
    mort
    -0.72
    woman
    -0.71
    ilater
    -0.68
    inqu
    -0.67
    buster
    -0.66
    killer
    -0.66
    places
    -0.66
    fired
    -0.66
    sets
    -0.66
    POSITIVE LOGITS
    SI
    1.09
    BILITIES
    0.86
    OLOG
    0.83
    FFER
    0.82
    pler
    0.81
    PLIC
    0.81
    UF
    0.80
    YA
    0.80
    EG
    0.79
    UE
    0.78
    Activations Density 0.007%

    No Known Activations