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. 24197
    Prev
    Next
    INDEX
    Explanations

    words related to wings or flying

    oai_token-act-pair · gpt-3.5-turbo

    references to "wings" or "wing-related" concepts

    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
    Interstitial
    -0.76
    ãĥ¤
    -0.75
     Cumber
    -0.74
     Uz
    -0.72
     metab
    -0.68
     Glock
    -0.68
    âĶĢâĶĢ
    -0.66
     WATCHED
    -0.64
     Scotia
    -0.64
     Nare
    -0.63
    POSITIVE LOGITS
    tips
    1.34
    tip
    1.33
    nuts
    1.22
    nut
    1.09
    edly
    0.99
    pread
    0.96
    bill
    0.95
    wings
    0.93
    plane
    0.93
     Chun
    0.93
    Activations Density 0.023%

    No Known Activations