© 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. 5197
    Prev
    Next
    INDEX
    Explanations

    words related to locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo
    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
     Perkins
    -1.03
     Petersen
    -0.93
     PW
    -0.89
     Peck
    -0.82
     Pier
    -0.79
     SPD
    -0.76
     Schneider
    -0.76
     Phys
    -0.76
     whist
    -0.76
     SPI
    -0.75
    POSITIVE LOGITS
    al
    1.83
    AL
    1.78
    als
    1.53
    ala
    1.51
    alin
    1.44
    alam
    1.40
    alis
    1.39
    ali
    1.36
    aled
    1.36
    alg
    1.35
    Activations Density 0.264%

    No Known Activations