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. 7-RES-JB
    6. 18527
    Prev
    Next
    INDEX
    Explanations

    special characters that are similar to or consist of particular patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geries
    -0.73
    shire
    -0.71
     unborn
    -0.71
     distracting
    -0.71
     reconc
    -0.70
     scripted
    -0.69
     spotting
    -0.68
     timely
    -0.68
     outgoing
    -0.68
     tee
    -0.67
    POSITIVE LOGITS
    ç¥ŀ
    0.99
    âĸĦ
    0.92
    ÙĦ
    0.91
    ITAL
    0.87
    eor
    0.86
    ãĤµ
    0.85
    å§«
    0.85
    à¼
    0.85
    vre
    0.84
    ski
    0.83
    Activations Density 0.009%

    No Known Activations