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. 3951
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Lyell"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition and mention of the name "Ly" or variations of it in different contexts

    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
    perture
    -0.93
    raints
    -0.78
    atchewan
    -0.77
    sburgh
    -0.73
    boards
    -0.69
    ORTS
    -0.68
    ardless
    -0.67
    arthy
    -0.65
    ajor
    -0.64
    insula
    -0.64
    POSITIVE LOGITS
    rics
    0.93
    onel
    0.85
     Ly
    0.84
    nda
    0.84
    comed
    0.80
    mb
    0.80
    umen
    0.77
    hurst
    0.76
    rell
    0.74
    low
    0.74
    Activations Density 0.015%

    No Known Activations