© 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. 1-RES-JB
    11. 20049
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lie" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idental
    -0.83
    okers
    -0.80
    kefeller
    -0.76
    isco
    -0.76
    ocative
    -0.74
    ugal
    -0.71
    izoph
    -0.70
    ional
    -0.70
    iance
    -0.70
    ively
    -0.69
    POSITIVE LOGITS
    gie
    1.10
    utenant
    1.03
    lla
    0.92
    orie
    0.91
    llo
    0.90
    âĸ¬
    0.85
    tto
    0.80
    ga
    0.80
    ffe
    0.80
    lette
    0.79
    Activations Density 0.019%

    No Known Activations