© 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. 2282
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating duration or time frame

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "for" followed by numerical values indicating time spans or duration

    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
    quartered
    -0.62
    inese
    -0.62
    ranked
    -0.60
     approached
    -0.59
     Accessed
    -0.57
     Vs
    -0.56
    ials
    -0.55
     Difficulty
    -0.54
     Gained
    -0.53
    #$
    -0.53
    POSITIVE LOGITS
     eternity
    1.36
     awhile
    1.32
     foreseeable
    1.23
     years
    1.14
     decades
    1.08
     future
    1.07
     generations
    1.01
     2019
    0.97
     months
    0.97
     sometime
    0.95
    Activations Density 0.178%

    No Known Activations