© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    references to mathematical problems and solutions

    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
    478
    +0.17
    0.9%
    413
    +0.12
    0.7%
    136
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.17
    -0.00
    17
    +0.12
    0.00
    271
    +0.12
    -0.00
    Negative Logits
    ));
    -1.73
    aign
    -1.64
    "));
    -1.60
     Devices
    -1.54
    ronic
    -1.49
    edia
    -1.48
    "})
    -1.47
     shall
    -1.45
     herein
    -1.45
     */,
    -1.44
    POSITIVE LOGITS
    Īĺ
    2.51
    ĻĤ
    2.49
    ĭ
    2.33
    Ĭ
    2.28
    ¯
    2.23
    ¿
    2.14
    IJ
    2.11
    ¾
    2.08
    §
    1.98
    Ī
    1.95
    Activations Density 0.245%

    No Known Activations