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. 10-RES-JB
    6. 15032
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or court documents

    oai_token-act-pair · gpt-3.5-turbo

    references to court proceedings and legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.75
     Saban
    -0.71
     sow
    -0.63
     OD
    -0.63
    mson
    -0.61
     Pyro
    -0.61
     todd
    -0.61
     Motorsport
    -0.60
    yip
    -0.59
     Leone
    -0.59
    POSITIVE LOGITS
    rooms
    1.49
    room
    1.23
    esan
    1.22
     martial
    1.06
    auld
    1.03
     proceedings
    1.02
    iers
    0.99
     filings
    0.96
    ney
    0.93
     rulings
    0.90
    Activations Density 0.040%

    No Known Activations