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. 0-RES-JB
    6. 17641
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by statements or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    the word "We" indicating collective or group statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.66
    epad
    -0.65
     bothered
    -0.61
    _>
    -0.56
    SPONSORED
    -0.55
    NetMessage
    -0.54
    -$
    -0.54
    ouver
    -0.53
    ãĥ©ãĥ³
    -0.52
    olor
    -0.52
    POSITIVE LOGITS
     We
    2.91
     Our
    2.17
    We
    2.09
    Our
    1.67
    we
    1.62
     WE
    1.52
     we
    1.50
     You
    1.38
     ourselves
    1.37
     Let
    1.29
    Activations Density 0.053%

    No Known Activations