© 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. 8-RES-JB
    11. 3412
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and events

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related events or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preserves
    -0.67
     arteries
    -0.63
    edia
    -0.63
    agnetic
    -0.60
    onis
    -0.59
     unfocusedRange
    -0.58
    erate
    -0.57
    orable
    -0.57
     starve
    -0.56
    USA
    -0.56
    POSITIVE LOGITS
     drafting
    0.80
     questioning
    0.80
     viewing
    0.78
     outset
    0.77
     inception
    0.76
     brainstorm
    0.76
     hearing
    0.74
    sbm
    0.72
     typing
    0.70
     interviewing
    0.68
    Activations Density 0.446%

    No Known Activations