Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23790
    Prev
    Next
    INDEX
    Explanations

    the duration of time, specifically in terms of weeks and months

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     republic
    -0.68
    osit
    -0.67
    rador
    -0.65
    iri
    -0.63
    icle
    -0.61
     hon
    -0.61
    spe
    -0.61
     lunch
    -0.60
    DAQ
    -0.59
     Faculty
    -0.58
    POSITIVE LOGITS
     Weeks
    3.43
     Woo
    1.08
     Phelps
    0.80
     Months
    0.80
     Sear
    0.78
     Walls
    0.77
     Till
    0.75
    henko
    0.73
    oulos
    0.72
     berth
    0.71
    Activations Density 0.018%

    No Known Activations