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. 2456
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ross."

    oai_token-act-pair · gpt-3.5-turbo
    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
    rious
    -0.76
    ACTED
    -0.73
     à¨
    -0.73
    rous
    -0.70
    lder
    -0.67
    brance
    -0.65
    ASED
    -0.64
     Countdown
    -0.64
     conspicuous
    -0.62
    urated
    -0.62
    POSITIVE LOGITS
    etti
    1.02
    bach
    1.02
    iter
    0.97
    olini
    0.92
    inson
    0.92
    andowski
    0.89
    aunders
    0.89
    endale
    0.85
    andra
    0.84
    lyn
    0.83
    Activations Density 0.030%

    No Known Activations