© 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. 421
    Prev
    Next
    INDEX
    Explanations

    references to the term "Lo" followed by a numeric value, possibly related to a specific entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lo" and its variations

    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
    manship
    -0.80
    pillar
    -0.60
     hardest
    -0.60
    metic
    -0.58
    ments
    -0.58
    rations
    -0.56
    master
    -0.56
    foundland
    -0.56
    uru
    -0.56
    EMENT
    -0.55
    POSITIVE LOGITS
    veland
    1.27
    fty
    1.21
    fts
    1.07
    vel
    1.04
    oming
    1.02
    ose
    0.99
    Gi
    0.97
    athing
    0.97
    vers
    0.97
    osen
    0.97
    Activations Density 0.026%

    No Known Activations