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. 18574
    Prev
    Next
    INDEX
    Explanations

    keywords related to data collection and processing

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that involve the word "and."

    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
     Bos
    -0.70
    Oracle
    -0.65
    Hart
    -0.65
    lon
    -0.61
     Wells
    -0.60
     Spears
    -0.60
    Ŀ
    -0.60
    Truth
    -0.60
    åij
    -0.60
     Despair
    -0.60
    POSITIVE LOGITS
     manipulate
    0.84
    rogens
    0.84
    pload
    0.82
     consume
    0.82
     transmit
    0.79
     analyze
    0.79
     obey
    0.76
     distribute
    0.76
     consumes
    0.76
     publish
    0.74
    Activations Density 0.126%

    No Known Activations