© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    references to the United States federal government and its agencies

    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
    71
    +0.14
    0.7%
    271
    +0.12
    0.6%
    224
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.14
    0.01
    350
    +0.12
    0.01
    55
    +0.11
    0.01
    Negative Logits
    tons
    -1.84
    ulators
    -1.65
    ulator
    -1.56
    itively
    -1.56
    iasis
    -1.55
    curs
    -1.53
    adeon
    -1.52
    robl
    -1.51
    ritic
    -1.48
    itives
    -1.47
    POSITIVE LOGITS
     STATES
    2.89
    Ľ
    2.18
    ®
    2.12
    ¸
    2.02
     Bureau
    1.96
    »
    1.93
    ½
    1.87
     Sentencing
    1.85
    Ļ
    1.82
    ¶
    1.73
    Activations Density 0.040%

    No Known Activations