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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12619
    Prev
    Next
    INDEX
    Explanations

    references to Comic-Con events and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to comic conventions and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.83
    metic
    -0.77
    attled
    -0.75
    etheless
    -0.75
    uckland
    -0.74
    ntil
    -0.74
    manent
    -0.73
    loo
    -0.73
    undai
    -0.72
    nah
    -0.72
    POSITIVE LOGITS
     Expo
    1.06
     Comic
    0.95
     Relief
    0.95
     Comics
    0.93
     Convention
    0.85
    afort
    0.84
    Age
    0.83
     merch
    0.82
     Merch
    0.81
     Store
    0.81
    Activations Density 0.023%

    No Known Activations