© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19022
    Prev
    Next
    INDEX
    Explanations

    phrases or words with a symbol or character followed by 'âĢ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I’m" or similar first-person expressions conveying personal sentiment

    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
     Zup
    -0.71
     Tid
    -0.69
     whichever
    -0.68
     guiActiveUnfocused
    -0.66
     dispers
    -0.66
     scattering
    -0.63
     feeding
    -0.62
     Palest
    -0.62
     Yon
    -0.62
     publicity
    -0.60
    POSITIVE LOGITS
    ª
    1.37
    £
    1.22
    Ķ
    1.19
    ¤
    1.17
    ¢
    1.16
    ¬
    1.16
    ķ
    1.15
    ¼
    1.14
    «
    1.13
    ¡
    1.11
    Activations Density 0.111%

    No Known Activations