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. 4-RES-JB
    6. 17855
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Huffington Post."

    oai_token-act-pair · gpt-3.5-turbo

    the frequent repetition of the term "Huffington Post."

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

    No Comments

    Negative Logits
    eding
    -0.73
    xual
    -0.73
    venants
    -0.69
    eded
    -0.68
    xon
    -0.68
    BuyableInstoreAndOnline
    -0.68
    luster
    -0.67
    etting
    -0.66
     Townsend
    -0.65
    arbon
    -0.65
    POSITIVE LOGITS
     Huffington
    0.90
    sylv
    0.85
    ãĥķãĤ¡
    0.79
     Post
    0.76
    ileaks
    0.73
    odox
    0.71
    Post
    0.69
    ienne
    0.68
    ãĤ·
    0.68
     Gazette
    0.66
    Activations Density 0.008%

    No Known Activations