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. 3825
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "redraw."

    oai_token-act-pair · gpt-3.5-turbo

    words related to exclusion or being left out

    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
    anooga
    -0.67
    rera
    -0.65
    king
    -0.65
    achine
    -0.64
    sburgh
    -0.62
    iman
    -0.61
    keley
    -0.60
    gee
    -0.60
    kee
    -0.60
    uador
    -0.59
    POSITIVE LOGITS
    Materials
    0.71
    ibilities
    0.70
    items
    0.67
     trove
    0.66
     annotations
    0.65
    utations
    0.63
    itives
    0.63
     deductions
    0.62
     enrichment
    0.61
    Memory
    0.61
    Activations Density 0.163%

    No Known Activations