© 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. 14119
    Prev
    Next
    INDEX
    Explanations

    numerical or mathematical expressions indicating positive and negative values

    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
    +0.15
    0.9%
    255
    +0.15
    0.9%
    391
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.15
    0.03
    391
    +0.15
    0.03
    177
    +0.13
    0.03
    Negative Logits
    ments
    -2.06
     sorts
    -1.90
    fully
    -1.73
    uded
    -1.54
    liest
    -1.53
    ment
    -1.50
     occupied
    -1.45
    :--
    -1.45
     include
    -1.44
     includes
    -1.41
    POSITIVE LOGITS
    ĨĴ
    2.86
    Ķ
    2.53
    ħ
    2.48
    ĵ
    2.40
    ĸ
    2.39
    Ŀ
    2.37
    Ĵ
    2.36
    Ļ
    2.33
    ĥ½
    2.32
                ↵
    2.28
    Activations Density 0.028%

    No Known Activations