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. 29570
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications or programming documentation

    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
    80
    +0.11
    0.6%
    154
    +0.11
    0.6%
    6
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.11
    0.05
    319
    +0.11
    0.04
    53
    +0.09
    0.05
    Negative Logits
    .”).
    -1.57
    ”).
    -1.55
    .’”
    -1.53
    .”
    -1.52
    ULTS
    -1.46
     Alzheimer
    -1.41
     soda
    -1.41
     sci
    -1.39
    EMENT
    -1.37
    ”),
    -1.36
    POSITIVE LOGITS
     */
    1.68
    ============
    1.57
     {#
    1.55
    https
    1.52
    ================================================
    1.48
     worth
    1.46
    msgstr
    1.45
    -------------------------------------------------------
    1.43
    ```
    1.42
    =====
    1.41
    Activations Density 0.345%

    No Known Activations