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. 7063
    Prev
    Next
    INDEX
    Explanations

    words related to wax and candles

    oai_token-act-pair · gpt-3.5-turbo

    references to types of wax and candles

    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
    arity
    -0.75
     Adin
    -0.71
    avez
    -0.71
    osuke
    -0.67
    HCR
    -0.66
    ICES
    -0.66
    ierrez
    -0.65
    ctica
    -0.65
    udder
    -0.65
    asio
    -0.64
    POSITIVE LOGITS
     wax
    1.04
     Wax
    0.89
    es
    0.84
     lyr
    0.83
    manship
    0.77
    ed
    0.76
    \\\\\\\\
    0.73
    paper
    0.72
    ing
    0.71
    works
    0.71
    Activations Density 0.020%

    No Known Activations