© 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. 32169
    Prev
    Next
    INDEX
    Explanations

    expressions of self-acceptance and personal happiness

    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
    186
    +0.25
    1.5%
    240
    +0.17
    1.0%
    342
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.25
    0.09
    240
    +0.17
    -0.05
    342
    +0.14
    0.05
    Negative Logits
    Īĺ
    -1.68
    @
    -1.52
    ))$
    -1.42
    °
    -1.42
    '))
    -1.41
    '));
    -1.36
     accordingly
    -1.34
    «
    -1.34
    respectively
    -1.30
     antagonist
    -1.29
    POSITIVE LOGITS
    idium
    1.55
    ussions
    1.42
    upid
    1.39
     Crick
    1.34
    ÃŃs
    1.31
    oubt
    1.31
    ISTER
    1.30
    "|
    1.30
    existent
    1.25
    angles
    1.25
    Activations Density 5.891%

    No Known Activations