© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    specific mentions of airline companies and countries

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" across various contexts in the text

    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
    leeve
    -0.71
    anooga
    -0.69
    cially
    -0.64
    IFA
    -0.64
     and
    -0.63
    cture
    -0.63
    INO
    -0.62
    zon
    -0.62
    adesh
    -0.61
     namely
    -0.61
    POSITIVE LOGITS
     ensuing
    1.20
     resultant
    1.10
     remainder
    1.08
     rest
    1.04
     accompanying
    1.02
     entire
    1.00
    ses
    0.99
     largest
    0.99
     vast
    0.98
     resulting
    0.98
    Activations Density 0.196%

    No Known Activations