© 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. 1-RES-SM
    11. 28576
    Prev
    Next
    INDEX
    Explanations

    phrases related to business negotiations and strategies

    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
    478
    +0.16
    0.9%
    23
    +0.16
    0.9%
    159
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.02
    111
    +0.16
    0.11
    338
    +0.10
    0.09
    Negative Logits
    emic
    -1.79
    itals
    -1.68
    ÃŃs
    -1.65
    emia
    -1.63
    omencl
    -1.58
    aires
    -1.53
    oster
    -1.50
    naire
    -1.48
    itures
    -1.47
    ÈĽ
    -1.46
    POSITIVE LOGITS
    done
    1.63
     God
    1.53
     LORD
    1.49
    woke
    1.48
    because
    1.47
     Okay
    1.45
     something
    1.45
    whether
    1.44
     nothing
    1.43
    ––––––––
    1.42
    Activations Density 1.121%

    No Known Activations