© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    references to new or updated things

    oai_token-act-pair · gpt-3.5-turbo

    references to "brand new" or new products and ideas

    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
    ulhu
    -0.85
    pmwiki
    -0.84
    cale
    -0.80
    veyard
    -0.79
    SEE
    -0.76
    abama
    -0.75
    DAY
    -0.73
     Able
    -0.67
    hower
    -0.67
    poons
    -0.66
    POSITIVE LOGITS
    ishing
    1.06
    ished
    0.96
    enburg
    0.95
     loyalty
    0.90
    ages
    0.87
    ishes
    0.84
    aging
    0.77
    brand
    0.76
    hetically
    0.73
    store
    0.73
    Activations Density 0.019%

    No Known Activations