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. 9-RES-JB
    6. 9539
    Prev
    Next
    INDEX
    Explanations

    adjectives describing difficulty or complexity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    but
    -0.83
    ructose
    -0.69
     But
    -0.66
    But
    -0.64
    hari
    -0.64
    ulhu
    -0.64
    eatured
    -0.63
    schild
    -0.63
    ukong
    -0.61
    perate
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.66
    etheless
    1.07
     anyway
    1.07
     nevertheless
    1.00
     anyways
    0.97
     owing
    0.82
    .[
    0.75
     because
    0.75
    .–
    0.74
     insofar
    0.72
    Activations Density 1.004%

    No Known Activations