© 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. 14746
    Prev
    Next
    INDEX
    Explanations

    words related to the Middle Eastern name "Hadi"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or regions

    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
    TON
    -0.74
    tle
    -0.72
    ridges
    -0.68
    take
    -0.68
    egg
    -0.67
    lishing
    -0.67
    ULAR
    -0.66
    glers
    -0.65
    ãĥ¼ãĥ«
    -0.64
    krit
    -0.63
    POSITIVE LOGITS
    Äĩ
    1.00
    adi
    0.85
    emi
    0.83
    atta
    0.83
    plom
    0.82
    obe
    0.80
    arbon
    0.79
    akh
    0.77
    ennes
    0.75
    udi
    0.75
    Activations Density 0.006%

    No Known Activations