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. 8-RES-JB
    6. 14703
    Prev
    Next
    INDEX
    Explanations

    positive adjectives related to the quality of products or services

    oai_token-act-pair · gpt-3.5-turbo

    positive adjectives describing products or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive adjectives related to the quality of products or services

    Explanation Uploaded by User

    adjectives

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usalem
    -0.68
    thood
    -0.65
    doms
    -0.63
    Progress
    -0.59
    ¬¼
    -0.58
    appiness
    -0.57
    zar
    -0.57
    ãĥİ
    -0.56
    xit
    -0.55
    ilings
    -0.54
    POSITIVE LOGITS
     compared
    0.98
     insofar
    0.96
     (~
    0.84
     indeed
    0.83
     mechanically
    0.80
     considering
    0.79
    looking
    0.79
     nowadays
    0.75
     tho
    0.75
     aest
    0.74
    Activations Density 0.305%

    No Known Activations