© 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. 27644
    Prev
    Next
    INDEX
    Explanations

    phrases related to research objectives and methodologies

    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
    263
    +0.12
    0.7%
    274
    +0.11
    0.7%
    313
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.12
    0.05
    500
    +0.11
    0.04
    274
    +0.11
    0.05
    Negative Logits
    isms
    -1.55
    ãĥ¼ãĤ¸
    -1.47
    eanor
    -1.42
    ism
    -1.41
    ctors
    -1.41
    ISM
    -1.40
    ા
    -1.39
    ி
    -1.36
     chatter
    -1.36
    gens
    -1.36
    POSITIVE LOGITS
    ĥ½
    1.61
    imme
    1.59
    unde
    1.56
    erad
    1.45
    prevent
    1.42
    anden
    1.38
    ketch
    1.35
    én
    1.34
    advant
    1.33
    ²
    1.31
    Activations Density 0.266%

    No Known Activations