Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11697
    Prev
    Next
    INDEX
    Explanations

    specific keywords and phrases related to financial and technological topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.29
    1.7%
    369
    +0.22
    1.3%
    240
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.29
    0.11
    410
    +0.22
    0.17
    484
    +0.13
    0.09
    Negative Logits
    etc
    -1.64
    ),\\
    -1.45
    "}](#
    -1.42
     ),
    -1.41
     etc
    -1.40
     );
    -1.39
    hearing
    -1.38
    issue
    -1.35
     ],
    -1.34
    inate
    -1.33
    POSITIVE LOGITS
     Disorders
    1.64
     Parenthood
    1.53
     rapidly
    1.43
     Comments
    1.35
     CONDITIONS
    1.34
    orphisms
    1.34
     DISCLAIM
    1.30
     Levels
    1.30
    apine
    1.30
     Parties
    1.30
    Activations Density 1.609%

    No Known Activations