© 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. 2-RES-SM
    11. 27746
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" and its frequency in various 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/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
    478
    +0.14
    0.8%
    387
    +0.12
    0.7%
    170
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.07
    440
    +0.12
    0.05
    387
    +0.12
    0.05
    Negative Logits
    ulation
    -1.79
    uality
    -1.70
    ulations
    -1.65
    isms
    -1.62
    imation
    -1.61
    iotics
    -1.58
    ware
    -1.57
    itious
    -1.56
     induced
    -1.56
     inactivated
    -1.52
    POSITIVE LOGITS
    »¿
    3.76
    ĥ½
    3.41
    ĻĤ
    3.40
    IJ
    3.39
    ¬
    3.32
    ³
    3.23
    ĥ
    3.20
    Īĺ
    3.18
    ½
    3.17
    ĸ´
    3.17
    Activations Density 0.214%

    No Known Activations