© 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. 2-RES-SM
    11. 31240
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their related substances

    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
    47
    +0.14
    0.8%
    320
    +0.14
    0.8%
    275
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.14
    0.02
    47
    +0.14
    0.03
    271
    +0.13
    0.00
    Negative Logits
    apest
    -1.67
    ieurs
    -1.67
    aliana
    -1.61
    aspx
    -1.52
    érie
    -1.51
    ocamp
    -1.46
    anmar
    -1.46
     ever
    -1.44
    adult
    -1.43
    ahoma
    -1.43
    POSITIVE LOGITS
    scill
    1.87
     mechanism
    1.80
     mechanisms
    1.76
     derived
    1.65
     removal
    1.65
     bioavailability
    1.63
     modifier
    1.62
    soluble
    1.60
    æº
    1.60
    eous
    1.58
    Activations Density 0.085%

    No Known Activations