© 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. 9-RES-JB
    11. 13789
    Prev
    Next
    INDEX
    Explanations

    times expressed in standardized time format (e.g., 5:00 a.m., 9:00 p.m.)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.66
     behav
    -0.63
     literature
    -0.63
     levers
    -0.57
    smanship
    -0.57
     unsus
    -0.56
     conson
    -0.56
     favour
    -0.56
     restrained
    -0.55
     Carbuncle
    -0.55
    POSITIVE LOGITS
    .,
    1.60
    .;
    1.35
    .?
    1.33
    .,"
    1.28
    .:
    1.25
    ./
    1.13
     EDT
    1.08
    .-
    1.05
    .—
    1.04
    .–
    1.03
    Activations Density 0.020%

    No Known Activations