© 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 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. 21530
    Prev
    Next
    INDEX
    Explanations

    words written in a specific script or language

    oai_token-act-pair · gpt-3.5-turbo

    words or characters from a specialized script or coding system

    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
     Appalach
    -0.75
     decomp
    -0.73
    Buyable
    -0.73
     Spartan
    -0.70
     Polaris
    -0.68
     Peel
    -0.68
    itaire
    -0.65
     Spartans
    -0.64
     Cena
    -0.63
     ESA
    -0.63
    POSITIVE LOGITS
    oÄŁ
    1.23
    ı
    1.16
    ÅŁ
    1.12
    ÄŁ
    1.07
    oÄŁan
    0.96
    ¶
    0.92
    istani
    0.92
    ·
    0.90
    dar
    0.89
     Tayyip
    0.87
    Activations Density 0.034%

    No Known Activations