© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30195
    Prev
    Next
    INDEX
    Explanations

    references to long-term implications or outcomes

    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
    400
    +0.15
    0.8%
    419
    +0.12
    0.7%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.15
    0.03
    400
    +0.12
    0.02
    121
    +0.12
    0.02
    Negative Logits
    ¦
    -3.06
    «
    -3.06
    ª
    -3.05
    ¯
    -2.93
    ¸
    -2.91
    İ
    -2.85
    ®
    -2.84
    ½
    -2.81
    ĥ
    -2.73
    Ĵ
    -2.73
    POSITIVE LOGITS
     exposure
    1.82
    olds
    1.78
     renewal
    1.65
     gains
    1.56
    uries
    1.52
     resolution
    1.52
     significance
    1.51
     relationships
    1.50
     (>
    1.50
    holds
    1.49
    Activations Density 0.107%

    No Known Activations