© 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. 31670
    Prev
    Next
    INDEX
    Explanations

    structured data formats or coding constructs

    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
    59
    +0.13
    0.7%
    478
    +0.12
    0.7%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.13
    0.04
    59
    +0.12
    0.04
    431
    +0.12
    0.03
    Negative Logits
    unov
    -1.52
    fecture
    -1.51
     approach
    -1.45
    wagen
    -1.45
     simulator
    -1.45
     issue
    -1.38
    stown
    -1.37
     [@
    -1.35
     theory
    -1.34
    gency
    -1.34
    POSITIVE LOGITS
    ĥ½
    3.68
    IJ
    3.54
    ĭ
    3.53
    <|padding|>
    3.48
    <|outofrange|>
    3.48
                  ↵
    3.48
    <|outofrange|>
    3.48
    ↵↵
    3.48
    ↵↵
    3.48
    3.48
    Activations Density 0.207%

    No Known Activations