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. 1-RES-JB
    6. 19185
    Prev
    Next
    INDEX
    Explanations

    names of sports players

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific athletes, particularly Derrick Rose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.76
    SY
    -0.72
    drive
    -0.69
    fare
    -0.69
    izoph
    -0.65
    rehens
    -0.64
    liament
    -0.64
    igation
    -0.63
     motto
    -0.61
    optim
    -0.60
    POSITIVE LOGITS
     Derrick
    1.07
     Jensen
    0.93
    rick
    0.81
    yers
    0.81
    leigh
    0.74
    hess
    0.73
    jit
    0.73
     Hendricks
    0.72
    hyde
    0.70
     Heist
    0.70
    Activations Density 0.005%

    No Known Activations