© 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. 24565
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or future planning

    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
    23
    +0.15
    0.9%
    83
    +0.13
    0.8%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.15
    0.05
    69
    +0.13
    0.05
    435
    +0.12
    0.04
    Negative Logits
    ĻĤ
    -3.57
    Ĵ
    -3.46
    İ
    -3.43
    IJ
    -3.31
    Ģ
    -3.15
    ¡
    -3.11
    ĩ
    -3.05
    ĭ
    -3.04
    Ĭ
    -3.03
    ī
    -3.00
    POSITIVE LOGITS
     kick
    1.76
     coast
    1.70
     hurt
    1.64
    wed
    1.55
    oes
    1.54
     haul
    1.53
    oms
    1.51
    ws
    1.51
     install
    1.51
     hell
    1.45
    Activations Density 0.339%

    No Known Activations