© 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. 0-RES-JB
    11. 13030
    Prev
    Next
    INDEX
    Explanations

    mentions of the city or region "Bil"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soda
    -0.81
     Revenge
    -0.79
     Dreams
    -0.78
     Sahara
    -0.75
     Norse
    -0.72
    science
    -0.69
    Hub
    -0.67
    FACE
    -0.67
    uay
    -0.67
    wordpress
    -0.67
    POSITIVE LOGITS
    bil
    3.43
    hens
    2.28
    BIL
    1.19
    infeld
    1.10
    uble
    1.06
     Cull
    1.02
    oling
    0.92
     Miranda
    0.85
    qi
    0.83
    oÄŁan
    0.81
    Activations Density 0.045%

    No Known Activations