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. 9425
    Prev
    Next
    INDEX
    Explanations

    references to a character named "Dalek."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase 'Dalek' or variations of it

    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
    ItemTracker
    -0.82
    éĹĺ
    -0.82
     Lovecraft
    -0.78
    hift
    -0.73
     Parenthood
    -0.72
    ģĸ
    -0.71
    terday
    -0.67
    sburgh
    -0.66
    uyomi
    -0.65
    âĸĪâĸĪ
    -0.64
    POSITIVE LOGITS
    vik
    1.02
    inar
    1.01
    jan
    0.90
    pling
    0.90
    mor
    0.88
    der
    0.88
    ston
    0.86
    istry
    0.82
    pole
    0.82
    illon
    0.80
    Activations Density 0.021%

    No Known Activations