© 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. 28598
    Prev
    Next
    INDEX
    Explanations

    significant accomplishments and contributions of notable individuals

    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
    235
    +0.17
    1.0%
    302
    +0.14
    0.8%
    419
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.17
    0.09
    235
    +0.14
    0.12
    218
    +0.13
    0.10
    Negative Logits
    pshire
    -1.51
     DISTRICT
    -1.48
    $]{};
    -1.45
    adows
    -1.45
    xico
    -1.44
    findViewById
    -1.43
    psilon
    -1.43
    vous
    -1.41
    "}](#
    -1.41
    unreadable
    -1.39
    POSITIVE LOGITS
     retired
    1.68
    ¬
    1.56
     jokes
    1.41
    ainer
    1.39
    onymous
    1.39
    ¾
    1.38
     sport
    1.37
    ¿½
    1.35
     collabor
    1.34
     advanced
    1.34
    Activations Density 5.606%

    No Known Activations