© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical measures

    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
    295
    +0.14
    0.8%
    127
    +0.13
    0.7%
    492
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.14
    0.05
    408
    +0.13
    0.04
    436
    +0.12
    0.05
    Negative Logits
     whole
    -1.63
    load
    -1.56
     ain
    -1.50
    ]>
    -1.49
    axis
    -1.42
    apers
    -1.42
     tape
    -1.41
     heartbeat
    -1.40
     recently
    -1.39
    putation
    -1.39
    POSITIVE LOGITS
    dorff
    2.13
    umab
    1.86
    umi
    1.79
    hof
    1.68
    stadt
    1.67
    umu
    1.62
    ietz
    1.59
    sein
    1.54
    schild
    1.53
    uel
    1.53
    Activations Density 0.186%

    No Known Activations