© 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. 1-RES-SM
    11. 26379
    Prev
    Next
    INDEX
    Explanations

    symbols and notation related to mathematical expressions or structures

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    274
    +0.12
    0.7%
    470
    +0.12
    0.7%
    53
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.12
    0.02
    274
    +0.12
    0.02
    129
    +0.11
    0.00
    Negative Logits
     purification
    -1.83
     migrating
    -1.69
     masters
    -1.51
     *)
    -1.50
    coming
    -1.48
     attachment
    -1.45
    stick
    -1.42
    )<
    -1.39
    hemer
    -1.39
    head
    -1.38
    POSITIVE LOGITS
    Īĺ
    1.75
    nier
    1.73
    ielle
    1.63
    epi
    1.58
     vu
    1.51
    Ī
    1.45
     evalu
    1.43
    ĻĤ
    1.41
    į
    1.40
    ariate
    1.40
    Activations Density 0.110%

    No Known Activations