© 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. 8-RES-JB
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    phrases related to daily routines or operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference daily routines or experiences

    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
    ãĥ¼ãĥĨ
    -0.77
    ãĤ¤ãĥĪ
    -0.71
    -+-+
    -0.68
    ãĥł
    -0.68
    uliffe
    -0.66
    ibly
    -0.66
    rencies
    -0.66
    etsy
    -0.65
    qus
    -0.65
    reau
    -0.65
    POSITIVE LOGITS
     reckoning
    0.94
    night
    0.85
    terday
    0.69
    sky
    0.68
    hours
    0.67
    ftime
    0.64
    day
    0.64
    recorded
    0.64
     Nights
    0.63
    morning
    0.63
    Activations Density 0.143%

    No Known Activations