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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3745
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or proper nouns, possibly related to a specific region or entity named "Calabria."

    oai_token-act-pair · gpt-3.5-turbo
    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
     Puzzle
    -0.70
    schild
    -0.68
    bley
    -0.66
    vae
    -0.64
     Sabha
    -0.61
    izont
    -0.61
    ellen
    -0.60
     Revenge
    -0.60
     Shutterstock
    -0.59
    etsk
    -0.59
    POSITIVE LOGITS
    ij士
    0.83
    ãĥĥãĥī
    0.77
    ornia
    0.77
    ãĤ¶
    0.73
    Ń·
    0.73
    veland
    0.71
    §
    0.70
    steen
    0.68
    ERO
    0.65
    ħ
    0.65
    Activations Density 0.118%

    No Known Activations