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. 6-RES-JB
    6. 6108
    Prev
    Next
    INDEX
    Explanations

    Italian football-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to the region of Italy and its name variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sworth
    -0.78
    inished
    -0.75
    iple
    -0.75
     glim
    -0.74
    orneys
    -0.73
    ager
    -0.72
    intosh
    -0.72
    itudes
    -0.71
    agers
    -0.71
    itude
    -0.71
    POSITIVE LOGITS
    utical
    1.01
    zza
    0.92
    zzo
    0.91
    ppe
    0.88
    ption
    0.86
    Äĩ
    0.81
    BILITY
    0.81
    emia
    0.80
    ÅŁ
    0.79
    lda
    0.78
    Activations Density 0.057%

    No Known Activations