© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    names or references to people and organizations

    oai_token-act-pair · gpt-3.5-turbo

    unique identifiers or names associated with specific entities or concepts

    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
    •EggList

    No Comments

    Negative Logits
     cycles
    -0.74
     Aura
    -0.68
    âĹı
    -0.67
    thumbnails
    -0.67
    awn
    -0.67
     Avatar
    -0.67
     MAP
    -0.66
    aura
    -0.66
     prototyp
    -0.65
     Scythe
    -0.65
    POSITIVE LOGITS
    f
    1.22
    F
    1.19
    Fs
    1.15
    FA
    1.04
    fi
    1.03
    fa
    1.02
    fen
    1.02
    fu
    1.01
    ff
    0.98
    fw
    0.98
    Activations Density 0.275%

    No Known Activations