© 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. 6-RES-JB
    11. 11770
    Prev
    Next
    INDEX
    Explanations

    locations or names related to "Panamanian"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "aman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.72
     Scand
    -0.68
    REE
    -0.66
    BM
    -0.64
    llor
    -0.63
    rees
    -0.63
    imilar
    -0.61
     Canaver
    -0.61
    regular
    -0.59
     Magnus
    -0.58
    POSITIVE LOGITS
    tha
    1.21
    ican
    1.11
    icans
    1.00
    icate
    0.99
    ica
    0.99
    ufact
    0.97
    ifest
    0.95
    ovic
    0.94
    nery
    0.93
    ned
    0.89
    Activations Density 0.028%

    No Known Activations