© 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. 27964
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships or connections

    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
    458
    +0.11
    0.6%
    156
    +0.11
    0.6%
    508
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.11
    0.00
    29
    +0.11
    0.00
    311
    +0.10
    0.00
    Negative Logits
     loyal
    -1.47
     Male
    -1.46
    idth
    -1.44
    umbs
    -1.39
    ophila
    -1.35
     sed
    -1.34
    atile
    -1.32
     Pill
    -1.32
    ide
    -1.31
    äng
    -1.31
    POSITIVE LOGITS
    lights
    1.99
     extinction
    1.73
    _);
    1.71
    –
    1.63
    going
    1.60
    mentioned
    1.56
    $–
    1.46
     happening
    1.46
     sclerosis
    1.44
    nement
    1.41
    Activations Density 0.000%

    No Known Activations