© 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. 32146
    Prev
    Next
    INDEX
    Explanations

    complex numbers and file paths

    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
    224
    +0.11
    0.6%
    45
    +0.11
    0.6%
    314
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.11
    0.06
    271
    +0.11
    0.02
    59
    +0.11
    0.05
    Negative Logits
    hin
    -1.50
    of
    -1.35
    awa
    -1.34
    Cause
    -1.34
    mouth
    -1.33
    following
    -1.31
    rooms
    -1.30
    wards
    -1.29
    ’
    -1.28
    !");
    -1.24
    POSITIVE LOGITS
    ¿
    3.44
    °
    3.03
    ±
    2.83
    ¾
    2.60
    ¸
    2.56
    ½
    2.54
    ŀ
    2.53
    ĻĤ
    2.52
    º
    2.51
    İ
    2.50
    Activations Density 0.367%

    No Known Activations