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. 2-RES-JB
    6. 16176
    Prev
    Next
    INDEX
    Explanations

    words related to praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hail" and its forms, particularly in contexts of praise or celebration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.82
    xus
    -0.79
    etry
    -0.75
    enhagen
    -0.73
    olves
    -0.70
    atalie
    -0.70
    omaly
    -0.69
    intendent
    -0.69
    arya
    -0.69
    essee
    -0.68
    POSITIVE LOGITS
     hailed
    1.06
    STON
    0.77
    ãĤ´
    0.74
     praise
    0.73
    EH
    0.70
     abroad
    0.69
     Mb
    0.68
     praises
    0.67
     praised
    0.67
    SHA
    0.67
    Activations Density 0.008%

    No Known Activations