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

    Neuronpedia

    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. 11-RES-JB
    11. 21961
    Prev
    Next
    INDEX
    Explanations

    words related to specific names and entities

    oai_token-act-pair · gpt-3.5-turbo

    tokens that indicate communication or statements about concerns, events, or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Libre
    -0.78
     Pupp
    -0.76
     spinach
    -0.75
     gren
    -0.73
     Gren
    -0.73
     Plex
    -0.72
     Garn
    -0.72
     cor
    -0.71
     darts
    -0.71
    Shadow
    -0.71
    POSITIVE LOGITS
     Ah
    1.81
    Ah
    1.70
    AH
    1.68
    ah
    1.68
     Bah
    1.51
    bah
    1.47
     ah
    1.46
     Ahmad
    1.45
     AH
    1.44
    ahs
    1.43
    Activations Density 0.248%

    No Known Activations