Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4581
    Prev
    Next
    INDEX
    Explanations

    instances of offers, requests, or suggestions being made

    oai_token-act-pair · gpt-3.5-turbo
    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
    è¦ļéĨĴ
    -0.89
    efeated
    -0.78
    ©¶æ¥µ
    -0.75
    quickShipAvailable
    -0.74
    itiveness
    -0.71
    usterity
    -0.68
    ãĥ³ãĤ¸
    -0.68
    ãĤ§
    -0.67
    icipated
    -0.67
    £ı
    -0.66
    POSITIVE LOGITS
     accompany
    1.38
     lend
    1.20
     borrow
    1.11
     escort
    1.09
     tutor
    1.08
     help
    1.07
     assist
    1.04
     join
    1.04
     babys
    1.01
     marry
    0.99
    Activations Density 0.275%

    No Known Activations