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

    Neuronpedia

    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. 9517
    Prev
    Next
    INDEX
    Explanations

    terms related to specific organizations or locations with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, organizations, or notable subjects

    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
    ived
    -0.59
     Bod
    -0.53
    rb
    -0.52
    ãģ¯
    -0.51
    idth
    -0.50
    rss
    -0.50
     Brit
    -0.50
    nos
    -0.49
    raw
    -0.48
    Ô
    -0.48
    POSITIVE LOGITS
     rul
    0.61
     phenotype
    0.57
     holdings
    0.54
     itself
    0.54
     herself
    0.51
     Citadel
    0.50
     apparatus
    0.49
     himself
    0.48
     shenan
    0.48
    agine
    0.47
    Activations Density 1.117%

    No Known Activations