© 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. 1-RES-SM
    11. 28717
    Prev
    Next
    INDEX
    Explanations

    conditional statements and questions regarding personal circumstances or situations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    283
    +0.13
    0.7%
    285
    +0.12
    0.7%
    263
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.13
    0.05
    283
    +0.12
    0.05
    285
    +0.11
    0.06
    Negative Logits
    iest
    -1.42
    iers
    -1.36
    :</
    -1.36
    top
    -1.34
    ãģ¾ãģĹãģŁ
    -1.34
    WARD
    -1.33
    ontal
    -1.32
    ↵³³
    -1.32
    év
    -1.31
    ursuant
    -1.29
    POSITIVE LOGITS
    naments
    2.21
    lete
    1.68
    chid
    1.67
     equivalently
    1.59
    bital
    1.55
     alternatively
    1.52
    gia
    1.49
    atase
    1.44
     anything
    1.41
    ci
    1.40
    Activations Density 0.860%

    No Known Activations