© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 12267
    Prev
    Next
    INDEX
    Explanations

    indicators of specific types of objects or entities in a technical context

    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
    478
    +0.16
    1.0%
    397
    +0.16
    0.9%
    156
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.16
    0.05
    291
    +0.16
    0.04
    137
    +0.15
    0.07
    Negative Logits
    à±ģ
    -2.14
    à±į
    -2.03
    à±
    -1.76
     Ages
    -1.76
    à¬
    -1.75
    iest
    -1.75
    à°¿
    -1.71
    rang
    -1.65
    opan
    -1.65
    еÑģк
    -1.56
    POSITIVE LOGITS
     few
    1.83
     consequent
    1.79
     reminder
    1.76
     believer
    1.73
     corresponding
    1.70
    cknowled
    1.69
     correspondingly
    1.69
     bunch
    1.67
     permanent
    1.67
     television
    1.59
    Activations Density 0.461%

    No Known Activations