© 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. 26802
    Prev
    Next
    INDEX
    Explanations

    phrases related to products that are designed or engineered for specific purposes

    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
    367
    +0.12
    0.7%
    309
    +0.12
    0.7%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.12
    0.03
    367
    +0.12
    0.02
    417
    +0.11
    0.02
    Negative Logits
    ĥ
    -1.60
    £
    -1.59
    clerosis
    -1.49
    áĢº
    -1.48
    und
    -1.46
    ĥ½
    -1.46
    CHANTABILITY
    -1.46
    conviction
    -1.45
    angered
    -1.41
    Ł
    -1.40
    POSITIVE LOGITS
     loosely
    1.71
    er
    1.64
     otherwise
    1.52
     specifically
    1.49
    otherwise
    1.49
    ially
    1.47
    ties
    1.45
     designs
    1.44
     to
    1.39
    urally
    1.38
    Activations Density 0.092%

    No Known Activations