© 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. 12-RES-JB
    11. 4164
    Prev
    Next
    INDEX
    Explanations

    common nouns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to notable historical events or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    detail
    -0.73
     Github
    -0.58
     fingerprints
    -0.57
    },{"
    -0.56
     printed
    -0.55
    ticket
    -0.55
    ById
    -0.55
     reversed
    -0.54
     kindred
    -0.54
     endorsed
    -0.54
    POSITIVE LOGITS
     period
    1.45
    period
    1.33
     periods
    1.30
     Period
    1.24
     season
    1.17
     era
    1.17
    imester
    1.13
     phase
    1.09
     years
    1.09
     months
    1.09
    Activations Density 0.373%

    No Known Activations