© 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. 4-RES-SM
    11. 14964
    Prev
    Next
    INDEX
    Explanations

    numerical addresses or contact information

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    17
    +0.11
    0.6%
    306
    +0.10
    0.6%
    456
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.11
    0.04
    477
    +0.10
    0.05
    129
    +0.10
    0.02
    Negative Logits
    Īĺ
    -2.03
    ĻĤ
    -1.89
    Ĩ
    -1.66
    ical
    -1.61
    ©
    -1.59
     much
    -1.59
    ization
    -1.58
    ospace
    -1.53
     whole
    -1.53
    raints
    -1.53
    POSITIVE LOGITS
     Avenue
    1.88
    й
    1.86
    MHz
    1.74
     Squadron
    1.67
    uncture
    1.61
    km
    1.59
     acres
    1.59
    mph
    1.58
    ammers
    1.57
     kilometres
    1.55
    Activations Density 0.309%

    No Known Activations