© 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. 27653
    Prev
    Next
    INDEX
    Explanations

    mentions of high-definition (HD) content or formats

    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
    334
    +0.17
    1.0%
    369
    +0.13
    0.7%
    269
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.17
    0.02
    25
    +0.13
    0.02
    269
    +0.12
    0.02
    Negative Logits
    IJ
    -2.89
    µ
    -2.81
    ĺ
    -2.80
    «
    -2.75
    ij
    -2.75
    ķ
    -2.74
    Īĺ
    -2.67
    Ĥ
    -2.66
    Ĺ
    -2.51
    Ī
    -2.51
    POSITIVE LOGITS
     Entertainment
    1.92
    MI
    1.89
     Broadcasting
    1.88
    TV
    1.77
    eno
    1.72
     Arts
    1.72
     Sports
    1.71
    ong
    1.67
     Records
    1.60
     Productions
    1.57
    Activations Density 0.110%

    No Known Activations