© 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. 29654
    Prev
    Next
    INDEX
    Explanations

    responses indicating agreement or affirmation

    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
    369
    +0.16
    0.9%
    326
    +0.15
    0.9%
    198
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.16
    0.05
    369
    +0.15
    0.02
    339
    +0.11
    0.03
    Negative Logits
    ¼
    -2.31
    ĨĴ
    -1.95
    ĭ
    -1.94
    Ļª
    -1.93
    º
    -1.87
    Ĺ
    -1.84
    ©
    -1.81
    Ļ
    -1.81
    ľĵ
    -1.79
    ²
    -1.78
    POSITIVE LOGITS
     Answer
    1.87
    Answer
    1.76
    ologia
    1.63
     worry
    1.59
     Question
    1.49
    :**
    1.47
     answer
    1.44
    :_
    1.38
     objection
    1.36
    oxford
    1.35
    Activations Density 1.152%

    No Known Activations