© 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. 9-RES-JB
    11. 1895
    Prev
    Next
    INDEX
    Explanations

    special characters likely specific to the model, potentially used as markers or embeddings for certain concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.81
     Robot
    -0.80
     crocod
    -0.77
     Haku
    -0.76
     Ag
    -0.76
     Sob
    -0.72
     Tier
    -0.72
     Solomon
    -0.71
     Liter
    -0.70
     Ide
    -0.70
    POSITIVE LOGITS
    Loading
    1.27
    together
    1.27
    ó
    1.22
    matter
    1.20
    Page
    1.18
    Commission
    1.18
    older
    1.18
    administ
    1.17
    that
    1.17
    said
    1.17
    Activations Density 0.196%

    No Known Activations