© 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. 32242
    Prev
    Next
    INDEX
    Explanations

    properties and attributes within structured contexts, such as code or data definitions

    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
    198
    +0.20
    1.1%
    419
    +0.13
    0.8%
    107
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.20
    0.08
    232
    +0.13
    0.15
    198
    +0.12
    0.09
    Negative Logits
    lington
    -1.54
     kingdom
    -1.51
    ://
    -1.51
    ffic
    -1.48
    Pal
    -1.41
    ora
    -1.40
    chle
    -1.38
    '));
    -1.38
    icle
    -1.38
    stown
    -1.38
    POSITIVE LOGITS
    ¸
    2.56
    Ŀ
    2.51
    Į
    2.51
    ©
    2.47
    Ĥ
    2.33
    ĩ
    2.25
    ĻĤ
    2.22
    ģ
    2.17
    İ
    2.16
    °
    2.15
    Activations Density 4.496%

    No Known Activations