© 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. 29481
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "work" indicating effort or collaboration

    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
    144
    +0.15
    0.8%
    318
    +0.14
    0.8%
    184
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.15
    0.04
    184
    +0.14
    0.04
    462
    +0.14
    0.03
    Negative Logits
    Ĩ
    -4.17
    Ħ
    -3.84
    Ī
    -3.80
    ľ
    -3.61
    ĥ
    -3.35
    ļ
    -3.31
    Ģ
    -3.26
    ħ
    -3.19
    Ń
    -3.18
    ij
    -3.18
    POSITIVE LOGITS
    emann
    2.09
    hower
    1.85
    stown
    1.82
    ington
    1.64
    horse
    1.62
    shire
    1.58
    emis
    1.58
    station
    1.56
    load
    1.55
    bench
    1.55
    Activations Density 0.141%

    No Known Activations