© 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. 11-RES-JB
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    hypertext links instructing to read or share a story

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.68
     tom
    -0.60
     jewels
    -0.59
    orsi
    -0.58
     accur
    -0.56
     locom
    -0.55
     grou
    -0.55
     manif
    -0.54
    hol
    -0.54
     fortun
    -0.54
    POSITIVE LOGITS
     Share
    1.03
     Subscribe
    0.81
     Download
    0.77
     Login
    0.77
     subscribe
    0.76
    lando
    0.74
     Write
    0.73
     Listen
    0.72
     Submit
    0.72
     bookmark
    0.70
    Activations Density 0.030%

    No Known Activations