© 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. 26403
    Prev
    Next
    INDEX
    Explanations

    logical connectors indicating options or combinations

    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
    209
    +0.18
    1.1%
    77
    +0.16
    0.9%
    491
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.18
    0.10
    494
    +0.16
    0.09
    77
    +0.14
    0.06
    Negative Logits
    uck
    -1.52
    $^{-
    -1.49
    adesh
    -1.48
     Today
    -1.44
    onents
    -1.44
    umps
    -1.43
     or
    -1.35
    zent
    -1.34
    override
    -1.33
    endants
    -1.33
    POSITIVE LOGITS
    chard
    1.47
    chte
    1.44
     unpaired
    1.43
     annealing
    1.42
    chan
    1.40
    ête
    1.39
    chio
    1.37
     HREF
    1.35
    ffic
    1.34
    glich
    1.32
    Activations Density 0.642%

    No Known Activations