© 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. 6281
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that occur annually

    oai_token-act-pair · gpt-3.5-turbo

    references to occurrences or statistics that happen annually

    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
    ymes
    -0.74
    ect
    -0.71
    otto
    -0.68
    jri
    -0.67
    tymology
    -0.65
    icators
    -0.61
     gravity
    -0.61
    arty
    -0.60
    aleb
    -0.60
    irs
    -0.60
    POSITIVE LOGITS
     thereafter
    0.81
     consecut
    0.72
     Supplement
    0.68
    Subscribe
    0.68
     upkeep
    0.68
     Iw
    0.67
     cycle
    0.66
    lot
    0.65
     ago
    0.64
     Polic
    0.64
    Activations Density 0.038%

    No Known Activations