© 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. 20687
    Prev
    Next
    INDEX
    Explanations

    locations or venues for events

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and their associated details

    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
    olson
    -0.81
    TOR
    -0.76
    Ott
    -0.75
     IST
    -0.74
    JP
    -0.70
     Nieto
    -0.69
    Toronto
    -0.69
     Ankara
    -0.68
    ++++
    -0.65
     Erdogan
    -0.64
    POSITIVE LOGITS
     Ky
    0.89
    Va
    0.89
     Tenn
    0.88
     Va
    0.87
     Ga
    0.76
     Ark
    0.75
     Md
    0.74
     South
    0.72
     Vir
    0.71
     Miss
    0.70
    Activations Density 0.110%

    No Known Activations