© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14054
    Prev
    Next
    INDEX
    Explanations

    references to network connectivity and technical specifications

    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
    156
    +0.20
    1.1%
    186
    +0.13
    0.8%
    484
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.20
    0.11
    409
    +0.13
    0.14
    423
    +0.12
    0.15
    Negative Logits
    ·¸
    -3.39
    ¸
    -3.36
    ³
    -3.10
    ij
    -3.09
    Ļ
    -3.07
    ²
    -3.02
    ĻĤ
    -3.02
    Ń
    -2.96
    ĥ½
    -2.95
    ¤
    -2.91
    POSITIVE LOGITS
    >`
    1.98
    /)
    1.76
    '):
    1.74
    /-/
    1.74
    %.
    1.73
    .<
    1.72
    pez
    1.69
    ?’
    1.68
    `.
    1.65
     #
    1.63
    Activations Density 4.935%

    No Known Activations