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. 10430
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Carmelo"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Carmelo" or similar variations

    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
    ãģį
    -0.86
     Fargo
    -0.74
     checkout
    -0.69
    Ń·
    -0.68
    uating
    -0.67
    lihood
    -0.65
    uates
    -0.63
    graduate
    -0.62
    uation
    -0.62
     Cherokee
    -0.62
    POSITIVE LOGITS
    ichael
    1.37
    ageddon
    1.18
    illo
    0.98
    agna
    0.97
     Carm
    0.95
    ony
    0.93
    eas
    0.91
    iac
    0.91
    agraph
    0.90
    anches
    0.90
    Activations Density 0.013%

    No Known Activations