© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20588
    Prev
    Next
    INDEX
    Explanations

    prices and numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and symbols, particularly related to financial information and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lub
    -0.85
     Slav
    -0.75
     Pork
    -0.67
     Sass
    -0.65
     Archangel
    -0.65
     Armenian
    -0.64
     Chambers
    -0.64
     plumbing
    -0.63
     Sheila
    -0.63
     Rud
    -0.62
    POSITIVE LOGITS
    99
    1.56
    499
    1.09
    999
    1.07
    995
    1.04
    49
    1.04
    95
    1.03
    299
    1.02
    59
    1.00
    599
    0.98
    199
    0.97
    Activations Density 0.015%

    No Known Activations