© 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. 9900
    Prev
    Next
    INDEX
    Explanations

    phrases related to work and productivity

    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
    198
    +0.13
    0.7%
    121
    +0.12
    0.7%
    245
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.13
    0.06
    406
    +0.12
    0.06
    282
    +0.11
    0.05
    Negative Logits
     votes
    -1.50
     review
    -1.44
    GREEK
    -1.41
     opinions
    -1.31
     born
    -1.31
     Review
    -1.29
     awards
    -1.29
     prize
    -1.27
     nombre
    -1.25
     influx
    -1.24
    POSITIVE LOGITS
    opy
    1.63
    ]{}.
    1.48
     ]{}
    1.45
    *]{}.
    1.42
    .]{}
    1.41
    oking
    1.40
     enough
    1.38
    enough
    1.37
    akes
    1.35
    ILE
    1.34
    Activations Density 0.661%

    No Known Activations