© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "cor-" which could be associated with terms like "corona" or "-correlation."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Cor," most likely referring to a specific person or entity throughout the document

    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
    lihood
    -1.00
    CRIP
    -0.76
     Merrill
    -0.72
    terday
    -0.70
     Jackets
    -0.61
     Hots
    -0.61
     Dangerous
    -0.61
     aloud
    -0.59
    TPS
    -0.58
     CPC
    -0.58
    POSITIVE LOGITS
    nered
    1.31
    bett
    1.25
    rupted
    1.25
    relation
    1.25
    bis
    1.18
    rupt
    1.13
    porate
    1.12
    nea
    1.11
    ruption
    1.10
    byn
    1.09
    Activations Density 0.019%

    No Known Activations