© 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. 25305
    Prev
    Next
    INDEX
    Explanations

    topics related to storytelling or narratives

    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
    154
    +0.12
    0.7%
    322
    +0.12
    0.7%
    293
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.12
    0.00
    28
    +0.12
    0.00
    371
    +0.11
    0.00
    Negative Logits
    Ĺ
    -1.71
    Ģ
    -1.60
    tn
    -1.60
    ¯
    -1.53
    nd
    -1.50
    ľ
    -1.50
    ¡
    -1.46
    µ
    -1.46
     colors
    -1.42
    bd
    -1.39
    POSITIVE LOGITS
     RFC
    1.89
    optera
    1.66
    vity
    1.50
     recruitment
    1.46
     invariance
    1.45
     anonymity
    1.45
     inception
    1.44
    ociety
    1.43
    corp
    1.43
    aurus
    1.39
    Activations Density 0.000%

    No Known Activations