© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9563
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week and the time of morning

    oai_token-act-pair · gpt-3.5-turbo

    references to specific times of the day, particularly in the morning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cient
    -0.73
    covered
    -0.71
    onductor
    -0.70
    ome
    -0.68
    atorial
    -0.67
    ittal
    -0.66
    risome
    -0.65
    insured
    -0.64
    chip
    -0.63
    ¤
    -0.63
    POSITIVE LOGITS
     afternoon
    0.76
     commute
    0.69
     mornings
    0.67
     evening
    0.67
     UPDATE
    0.67
     onwards
    0.66
     Evening
    0.64
     EST
    0.63
    endment
    0.63
     marked
    0.63
    Activations Density 0.038%

    No Known Activations