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. 4216
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or concept, like "Stranger"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Str" in various contexts, suggesting a focus on specific popular titles or brands

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    hyde
    -0.71
    ciation
    -0.70
    merce
    -0.68
    yright
    -0.67
    etheless
    -0.67
    peat
    -0.66
    eph
    -0.64
    delay
    -0.62
    bear
    -0.61
    POSITIVE LOGITS
    atton
    1.21
    ategy
    1.15
    anded
    1.03
    ife
    1.03
    ategic
    1.02
    ands
    1.00
    ainer
    0.99
    icken
    0.98
    ained
    0.97
    onge
    0.96
    Activations Density 0.021%

    No Known Activations