© 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. 10-RES-JB
    11. 4725
    Prev
    Next
    INDEX
    Explanations

    words related to walls

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "wall."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gene
    -0.76
     delegated
    -0.70
    phrine
    -0.70
    lihood
    -0.70
     Virtue
    -0.67
    milo
    -0.64
     Carbuncle
    -0.64
    MENTS
    -0.63
    orean
    -0.62
    URA
    -0.60
    POSITIVE LOGITS
    papers
    1.41
    aby
    1.22
    abies
    1.21
    paper
    1.13
    clock
    1.03
    owing
    0.99
     thickness
    0.98
    tops
    0.94
    owed
    0.94
     wart
    0.92
    Activations Density 0.022%

    No Known Activations