Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20505
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or victory

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or action in sports contexts

    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
    bidden
    -0.65
    eering
    -0.60
    Parents
    -0.59
    phant
    -0.59
    stice
    -0.59
    essa
    -0.58
    itudes
    -0.58
    creen
    -0.57
    theless
    -0.56
     Lol
    -0.56
    POSITIVE LOGITS
     undefeated
    1.03
     unbeaten
    0.95
     undrafted
    0.93
    nova
    0.79
    verning
    0.79
     toe
    0.79
    YN
    0.77
    lems
    0.76
    erenn
    0.74
     Klux
    0.74
    Activations Density 0.053%

    No Known Activations