© 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. 4-RES-SM
    11. 9015
    Prev
    Next
    INDEX
    Explanations

    references to corporations and corporate entities

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.16
    0.9%
    21
    +0.15
    0.8%
    107
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.16
    0.02
    425
    +0.15
    0.03
    213
    +0.11
    0.02
    Negative Logits
    ĥ½
    -3.54
    Ĺ
    -3.49
    -3.30
    -3.30
    <|outofrange|>
    -3.30
    -3.30
    -3.30
             ↵
    -3.30
    -3.30
    ↵
    -3.30
    POSITIVE LOGITS
    wide
    1.73
     Limited
    1.69
    sson
    1.64
     Ltd
    1.51
    als
    1.51
     logo
    1.50
    č↵č↵č
    1.48
     LIMITED
    1.47
    ounces
    1.47
    ){#
    1.46
    Activations Density 0.131%

    No Known Activations