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. 9-RES-JB
    6. 4063
    Prev
    Next
    INDEX
    Explanations

    verbs related to competition and victory

    oai_token-act-pair · gpt-3.5-turbo

    the concept of winning or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resa
    -0.64
    arin
    -0.63
    alore
    -0.59
    rehens
    -0.58
     lapse
    -0.57
    opian
    -0.56
    anwhile
    -0.55
    rimination
    -0.55
    Factor
    -0.54
    yrinth
    -0.54
    POSITIVE LOGITS
    now
    1.10
    nings
    0.98
     hearts
    0.88
    ests
    0.88
     prizes
    0.86
     trophies
    0.83
    ced
    0.80
     battles
    0.79
    throp
    0.77
    cest
    0.77
    Activations Density 0.061%

    No Known Activations