© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12951
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, specifically indicating a point in time

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal markers and conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    terday
    -0.76
     sails
    -0.75
    ħĭ
    -0.73
     subscrib
    -0.65
     plurality
    -0.63
     interchangeable
    -0.62
    NAS
    -0.61
    mouth
    -0.59
    mob
    -0.59
    loop
    -0.58
    POSITIVE LOGITS
    atto
    0.73
    iosyncr
    0.73
    elia
    0.73
    ividual
    0.66
    illes
    0.65
    hani
    0.65
    erest
    0.63
    xus
    0.62
    idia
    0.62
    illi
    0.62
    Activations Density 0.140%

    No Known Activations