© 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. 9555
    Prev
    Next
    INDEX
    Explanations

    mentions of the census and its associated statistics

    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
    71
    +0.15
    0.8%
    117
    +0.12
    0.7%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.15
    0.02
    335
    +0.12
    0.02
    117
    +0.12
    0.02
    Negative Logits
    ¶
    -4.73
    -4.51
    ↵
    -4.51
    -4.51
    -4.51
        ↵
    -4.51
    -4.51
    ↵↵↵
    -4.51
    -4.51
    -4.51
    POSITIVE LOGITS
    illac
    1.97
    fecture
    1.68
    ennial
    1.64
     era
    1.61
    atures
    1.60
     estimate
    1.59
    jiang
    1.59
     insign
    1.53
    IBLE
    1.46
    kom
    1.43
    Activations Density 0.145%

    No Known Activations