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. 23687
    Prev
    Next
    INDEX
    Explanations

    references to signings and contracts

    oai_token-act-pair · gpt-3.5-turbo

    words related to player signings and contracts in sports

    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
    adish
    -0.82
    ĸļ
    -0.80
    negie
    -0.71
    osate
    -0.70
    asures
    -0.68
    omal
    -0.63
    ixel
    -0.61
    rimination
    -0.60
    ooked
    -0.59
    opy
    -0.59
    POSITIVE LOGITS
     waivers
    1.07
    ificantly
    0.98
     contracts
    0.94
     aut
    0.88
     bonuses
    0.81
     deals
    0.81
     agreements
    0.80
    ually
    0.79
    deals
    0.79
     unrestricted
    0.78
    Activations Density 0.024%

    No Known Activations