© 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 EvalsExportsAPI 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. 9865
    Prev
    Next
    INDEX
    Explanations

    mentions of temperature or food descriptors related to heat

    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
    156
    +0.18
    1.0%
    477
    +0.14
    0.8%
    198
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.18
    0.03
    148
    +0.14
    0.01
    1
    +0.12
    0.02
    Negative Logits
    cción
    -1.62
    izumab
    -1.60
    unctive
    -1.59
    inib
    -1.54
    ção
    -1.54
     entirety
    -1.48
    inous
    -1.46
    üller
    -1.45
    uvant
    -1.40
     viability
    -1.40
    POSITIVE LOGITS
     Springs
    2.11
    ness
    2.05
    spots
    2.02
    plug
    1.88
     enough
    1.78
    lights
    1.71
    stuff
    1.71
    ford
    1.70
     springs
    1.69
    ened
    1.67
    Activations Density 0.152%

    No Known Activations