© 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. 1-RES-SM
    11. 29158
    Prev
    Next
    INDEX
    Explanations

    components related to data input and output processes in programming

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    217
    +0.13
    0.7%
    434
    +0.12
    0.7%
    433
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.13
    0.03
    224
    +0.12
    0.03
    301
    +0.11
    0.03
    Negative Logits
    ı
    -3.03
    ĩ
    -2.80
    ¹
    -2.76
    ĥ½
    -2.74
    ĺ
    -2.69
    ³
    -2.65
    Ł
    -2.64
    ĸ
    -2.63
    Ĺ
    -2.57
    ķ
    -2.57
    POSITIVE LOGITS
    maid
    1.60
    naire
    1.55
    Utils
    1.53
     Fargo
    1.52
    vie
    1.45
    wright
    1.40
    ocortic
    1.40
    builder
    1.38
    ERTY
    1.37
    pool
    1.33
    Activations Density 0.185%

    No Known Activations