© 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. 8-RES-JB
    11. 2005
    Prev
    Next
    INDEX
    Explanations

    numbers written in a specific format (such as dates, phone numbers, etc.)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numbers and their contexts in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.84
    lections
    -0.71
    adal
    -0.70
    colour
    -0.70
    aturdays
    -0.70
    ennial
    -0.68
    utra
    -0.68
    enary
    -0.67
    ertodd
    -0.67
    ysis
    -0.66
    POSITIVE LOGITS
    SPONSORED
    1.04
    PHOTOS
    0.95
     Inquis
    0.94
    According
    0.91
    advertising
    0.89
    Apparently
    0.86
    Meanwhile
    0.84
    Wow
    0.81
    RELATED
    0.80
    Fake
    0.80
    Activations Density 0.578%

    No Known Activations