© 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. 10602
    Prev
    Next
    INDEX
    Explanations

    hyperlinks within text

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" in various contexts

    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
     manif
    -0.67
     myster
    -0.62
     univers
    -0.59
     accur
    -0.58
    hower
    -0.58
     plent
    -0.57
    £ı
    -0.56
    ¬¼
    -0.56
     wolves
    -0.56
     desper
    -0.56
    POSITIVE LOGITS
     Share
    0.89
     subscribe
    0.88
     Subscribe
    0.80
     Download
    0.79
     Write
    0.77
    lando
    0.77
    Subscribe
    0.75
     Email
    0.75
    acle
    0.74
     Login
    0.74
    Activations Density 0.030%

    No Known Activations