© 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. 11-RES-JB
    11. 154
    Prev
    Next
    INDEX
    Explanations

    times of day written in a specific format (hours followed by minutes and optionally 'a.m.' or 'p.m.')

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asel
    -0.65
     Metatron
    -0.59
    uminium
    -0.56
    glomer
    -0.55
    $$
    -0.52
    Reviewer
    -0.52
    ãĥĺ
    -0.52
    Ó
    -0.52
    aced
    -0.51
    yles
    -0.51
    POSITIVE LOGITS
     p
    1.11
    pm
    0.99
     pm
    0.90
    PM
    0.88
    noon
    0.79
    icum
    0.74
     noon
    0.71
     PM
    0.70
    AM
    0.70
     Noon
    0.69
    Activations Density 0.053%

    No Known Activations