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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    inconsistent characters or unrecognized text patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    och
    -0.94
    cius
    -0.94
    arton
    -0.88
    onics
    -0.87
    hyde
    -0.85
    anza
    -0.85
    chio
    -0.85
    inar
    -0.83
    achy
    -0.82
    otype
    -0.82
    POSITIVE LOGITS
    ãĤī
    1.44
    ãģĦ
    1.43
    ãģ¾
    1.43
    ãĤ
    1.41
    ãģ
    1.41
    ãģŁ
    1.37
    ãģ¦
    1.34
    ãĤĵ
    1.31
    ãģĵ
    1.29
    ãģĭ
    1.29
    Activations Density 0.009%

    No Known Activations