© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    references to ethical considerations regarding the influence of external authorities on children

    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
    47
    +0.14
    0.8%
    125
    +0.14
    0.8%
    122
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.14
    0.19
    111
    +0.14
    0.15
    510
    +0.13
    0.19
    Negative Logits
    ,’
    -6.60
    .’
    -6.48
    ?’
    -6.41
    .’”
    -6.32
    ’.
    -5.96
    ’,
    -5.82
    !’
    -5.51
    ’
    -5.26
    ‘
    -4.21
    ?”
    -4.14
    POSITIVE LOGITS
     "
    5.55
     "[
    4.48
     "...
    4.34
     "`
    4.06
     "*
    4.01
     "(
    3.98
     "'
    3.92
     ("
    3.84
     ".
    3.56
    --"
    3.56
    Activations Density 4.178%

    No Known Activations