© 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. 16812
    Prev
    Next
    INDEX
    Explanations

    names related to certain professions or events

    oai_token-act-pair · gpt-3.5-turbo

    words that reference specific people, characters, or entities

    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
     class
    -0.56
     [âĢ¦]
    -0.56
     CONTR
    -0.56
     FAC
    -0.55
     curve
    -0.54
     ....
    -0.54
     passer
    -0.53
     [/
    -0.53
     DOI
    -0.53
     ***
    -0.52
    POSITIVE LOGITS
    orst
    0.87
    ÃŃn
    0.83
    idia
    0.78
    jen
    0.76
    kov
    0.75
    uter
    0.75
    aston
    0.72
    itan
    0.71
    enson
    0.71
    enges
    0.71
    Activations Density 0.362%

    No Known Activations