© 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. 8-RES-JB
    11. 1237
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming or technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the special character sequence "âĢ"

    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
     fortun
    -0.64
     horizont
    -0.62
     Faw
    -0.58
    anwhile
    -0.58
     interf
    -0.58
     seiz
    -0.58
     Tanz
    -0.58
     Marketable
    -0.58
    çīĪ
    -0.57
    æ©
    -0.57
    POSITIVE LOGITS
    ¬
    1.13
    Ļ
    1.12
    ¤
    1.02
    Ń
    1.02
    ĸ
    1.01
    ª
    0.98
    ķ
    0.98
    £
    0.97
    ľ
    0.97
    Ĵ
    0.96
    Activations Density 0.462%

    No Known Activations