© 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. 18466
    Prev
    Next
    INDEX
    Explanations

    references to the word "Sky"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Sky 2" entity or product

    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
    aneous
    -0.70
    ional
    -0.69
     thous
    -0.68
     Schne
    -0.68
    女
    -0.67
     insensitive
    -0.67
    ento
    -0.67
    Ñĭ
    -0.66
    ual
    -0.65
    hesis
    -0.65
    POSITIVE LOGITS
    hawk
    1.00
    fall
    0.97
    rocket
    0.96
    hawks
    0.96
    lake
    0.91
    fax
    0.90
    eus
    0.89
    landers
    0.86
    rock
    0.85
    lar
    0.84
    Activations Density 0.025%

    No Known Activations