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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26501
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving sets and array structures

    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
    277
    +0.12
    0.7%
    371
    +0.12
    0.7%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.12
    0.01
    221
    +0.12
    0.01
    349
    +0.11
    0.01
    Negative Logits
    ).[
    -1.75
    ysis
    -1.64
    )</
    -1.59
    }}</
    -1.53
    ));
    -1.51
    asks
    -1.50
    );
    -1.47
    .);
    -1.45
     lith
    -1.45
    inary
    -1.43
    POSITIVE LOGITS
    Ĭ
    2.60
    ĭ
    2.50
    ¿½
    2.24
    ĻĤ
    2.23
    ¬
    2.21
    ŀ
    2.15
    ¯
    2.13
    ¢
    2.11
    į
    2.11
    ĩ
    2.04
    Activations Density 0.073%

    No Known Activations