© 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. 9913
    Prev
    Next
    INDEX
    Explanations

    terms related to prediction and forecasting

    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
    156
    +0.14
    0.8%
    471
    +0.12
    0.7%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.14
    0.02
    404
    +0.12
    0.02
    471
    +0.11
    0.01
    Negative Logits
    ]>
    -1.49
    >(
    -1.49
    STIT
    -1.42
    >();
    -1.42
    pshire
    -1.39
    jours
    -1.39
     banc
    -1.39
    infty
    -1.39
    >()
    -1.38
    ramento
    -1.37
    POSITIVE LOGITS
    ably
    2.68
    iest
    1.60
    ms
    1.60
     games
    1.48
     heights
    1.47
    nament
    1.46
    uristic
    1.44
    ional
    1.44
    ationally
    1.43
     doom
    1.42
    Activations Density 0.183%

    No Known Activations