© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or name, likely "Ar" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the specific mention of "Ar" followed by a number, indicating characters or entities

    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
    eners
    -0.73
     sight
    -0.70
    ¬¼
    -0.69
     functioning
    -0.64
    eries
    -0.63
     goodbye
    -0.62
    iculty
    -0.61
    ĸļ
    -0.61
     pathology
    -0.60
    creen
    -0.60
    POSITIVE LOGITS
    ithmetic
    1.15
    ansas
    1.14
    thritis
    1.11
    ranged
    1.10
    rington
    1.03
    onson
    1.01
    rang
    1.01
    agon
    1.00
    beit
    0.99
    mit
    0.99
    Activations Density 0.017%

    No Known Activations