© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or entities named "Burn" followed by numerical values that indicate some kind of significance or relation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Burnham" across various contexts

    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
    ilial
    -0.73
    DonaldTrump
    -0.71
    mercial
    -0.66
     FINAL
    -0.66
    ploma
    -0.65
    ngth
    -0.65
    awaru
    -0.65
    ournal
    -0.64
    ensional
    -0.64
    ocre
    -0.62
    POSITIVE LOGITS
    burn
    1.01
    ished
    0.99
    er
    0.90
    aby
    0.90
    Burn
    0.90
    ards
    0.89
     Burn
    0.88
    burning
    0.86
    ishing
    0.82
     burn
    0.81
    Activations Density 0.016%

    No Known Activations