© 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. 10-RES-JB
    11. 11435
    Prev
    Next
    INDEX
    Explanations

    locations or destinations mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters in context

    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
    Ħ¢
    -0.72
    adelphia
    -0.67
     dime
    -0.64
     liner
    -0.64
    cule
    -0.64
    pheus
    -0.64
     tornado
    -0.63
    edy
    -0.62
     goofy
    -0.62
    berries
    -0.62
    POSITIVE LOGITS
    said
    1.16
    according
    1.13
     according
    1.04
     Sheikh
    1.02
     organisers
    0.98
    english
    0.98
     Kerala
    0.97
     said
    0.95
     Yad
    0.90
     Mohammad
    0.90
    Activations Density 0.395%

    No Known Activations