© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10142
    Prev
    Next
    INDEX
    Explanations

    dates in the format of "dayth"

    oai_token-act-pair · gpt-3.5-turbo

    dates and ordinal numbers

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

    No Comments

    Negative Logits
    GGGGGGGG
    -0.68
    acci
    -0.61
     styl
    -0.60
    mbuds
    -0.60
     pastoral
    -0.57
    essor
    -0.56
    rawdownloadcloneembedreportprint
    -0.56
     breeding
    -0.56
     portfolios
    -0.56
     animals
    -0.55
    POSITIVE LOGITS
    ioxide
    1.07
    ulhu
    0.94
     Amendment
    0.83
    umbnail
    0.82
    endment
    0.82
    ieth
    0.81
    icum
    0.81
    burgh
    0.80
     anniversary
    0.79
     Anniversary
    0.78
    Activations Density 0.017%

    No Known Activations