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. 3-RES-JB
    6. 11651
    Prev
    Next
    INDEX
    Explanations

    references to famous landmarks, particularly the "Eiffel Tower."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Eiffel Tower

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é»Ĵ
    -0.76
    ãģ®éŃĶ
    -0.73
    dit
    -0.72
    milo
    -0.71
    avez
    -0.71
    ãĤ±
    -0.70
    ppo
    -0.67
    ktop
    -0.65
    poll
    -0.64
    ERAL
    -0.63
    POSITIVE LOGITS
     Towers
    1.11
     Tower
    1.10
    tower
    1.00
     skysc
    0.98
     towers
    0.91
     Tycoon
    0.90
     tower
    0.89
    itect
    0.82
    fall
    0.81
    raper
    0.79
    Activations Density 0.010%

    No Known Activations