© 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. 29034
    Prev
    Next
    INDEX
    Explanations

    various usages of the word "to" in different contexts

    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
    114
    +0.14
    0.8%
    499
    +0.13
    0.7%
    190
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.04
    69
    +0.13
    0.06
    197
    +0.11
    0.03
    Negative Logits
    "></
    -1.72
    14514500
    -1.67
    ĻĤ
    -1.53
    1451450014514500
    -1.51
    "}](
    -1.47
    arf
    -1.47
    VD
    -1.46
    ·
    -1.46
    »
    -1.45
    Ĵ
    -1.44
    POSITIVE LOGITS
    oint
    1.71
     employers
    1.55
     whatsoever
    1.55
    ptions
    1.54
     arise
    1.49
     hypotheses
    1.47
    ments
    1.47
     respondents
    1.47
     instructors
    1.45
    isans
    1.43
    Activations Density 1.058%

    No Known Activations