© 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. 7-RES-JB
    11. 7239
    Prev
    Next
    INDEX
    Explanations

    time-related measurements like years, months, days, and hours

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.90
    ierrez
    -0.87
    acted
    -0.82
    JV
    -0.69
    kef
    -0.69
    Sov
    -0.69
    Reviewer
    -0.68
    dinand
    -0.68
    untled
    -0.67
    ersen
    -0.66
    POSITIVE LOGITS
     elapsed
    1.08
     Ago
    1.07
     ago
    1.05
     spent
    0.88
    cake
    0.84
    cale
    0.82
    glass
    0.80
     Ahead
    0.79
    pring
    0.75
    birth
    0.75
    Activations Density 0.181%

    No Known Activations