© 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. 9-RES-JB
    11. 7566
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the word "ice."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ice or icy conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajo
    -0.87
    omination
    -0.77
    yrinth
    -0.76
    asca
    -0.75
    lisher
    -0.73
    ged
    -0.73
    isco
    -0.70
    orers
    -0.70
    risk
    -0.70
    verty
    -0.70
    POSITIVE LOGITS
    lli
    1.35
    llular
    1.31
    lla
    1.14
    xp
    1.08
    utical
    1.04
    llo
    1.02
    ptive
    1.02
    llan
    1.01
    cream
    0.94
    ll
    0.87
    Activations Density 0.061%

    No Known Activations