© 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. 2-RES-JB
    11. 23712
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Down" with differing levels of emphasis or unrelated contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Down" or people associated with Down's syndrome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.92
    aceous
    -0.75
    ature
    -0.71
    ================================
    -0.71
    olulu
    -0.70
    à
    -0.69
    olkien
    -0.69
    andum
    -0.69
    ://
    -0.68
    atories
    -0.68
    POSITIVE LOGITS
    stairs
    1.50
    hill
    1.02
    graded
    0.97
    grades
    0.89
    stem
    0.87
    LOAD
    0.85
    grading
    0.83
    lap
    0.83
    stream
    0.83
    loaded
    0.83
    Activations Density 0.011%

    No Known Activations