© 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. 10-RES-JB
    11. 6582
    Prev
    Next
    INDEX
    Explanations

    phrases or names containing the letter "R"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific movies and their titles

    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
    é¾įå¥ij士
    -0.64
     diplom
    -0.63
    è£ħ
    -0.63
     avail
    -0.63
    ãĤ¤ãĥĪ
    -0.62
    CN
    -0.61
    erred
    -0.61
     acknow
    -0.61
     barring
    -0.60
    Ont
    -0.60
    POSITIVE LOGITS
    umps
    1.01
    apes
    0.99
    abbit
    0.99
    oots
    0.96
    ails
    0.93
    oses
    0.92
    ummies
    0.91
    uffs
    0.90
    ippers
    0.90
    ipper
    0.88
    Activations Density 0.124%

    No Known Activations