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. 14796
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols that are likely encoding artifacts

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, particularly the character "ü"

    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
    ividual
    -0.68
     Keeper
    -0.68
     Eaton
    -0.67
     Luther
    -0.65
    oreal
    -0.65
     Painter
    -0.64
     Bagg
    -0.64
    aged
    -0.64
    ieth
    -0.62
     Accord
    -0.62
    POSITIVE LOGITS
    ¶
    1.03
    ¿
    1.03
    ·
    1.03
    ¸
    0.98
    pees
    0.92
    ¬
    0.91
    ĸ
    0.91
    cks
    0.91
    ü
    0.90
    eh
    0.90
    Activations Density 0.014%

    No Known Activations