© 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. 10-RES-JB
    11. 3151
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or temporal events

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.95
    auga
    -0.70
    oS
    -0.69
     indo
    -0.66
     Consent
    -0.63
     Gleaming
    -0.63
    ystem
    -0.62
    Ô
    -0.62
     kinderg
    -0.62
     Da
    -0.61
    POSITIVE LOGITS
     finale
    0.85
    long
    0.76
     festivities
    0.75
    liest
    0.73
    finals
    0.71
    burn
    0.69
     opener
    0.65
    lies
    0.64
    forth
    0.64
    lynn
    0.62
    Activations Density 0.097%

    No Known Activations