© 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. 1-RES-SM
    11. 27320
    Prev
    Next
    INDEX
    Explanations

    terms and references related to resolution measurements in various contexts

    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
    156
    +0.16
    0.9%
    100
    +0.13
    0.7%
    224
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.16
    0.01
    473
    +0.13
    0.01
    100
    +0.11
    0.01
    Negative Logits
    iasis
    -2.03
     hav
    -1.59
    iquity
    -1.56
    ymoon
    -1.52
     sed
    -1.51
     expatri
    -1.50
     rude
    -1.49
     crazy
    -1.48
    ulance
    -1.47
     forth
    -1.46
    POSITIVE LOGITS
    table
    2.02
    etable
    1.91
    igned
    1.75
     table
    1.73
    imetry
    1.69
    creen
    1.64
    HB
    1.63
     achievable
    1.60
    CRIPT
    1.56
    ensor
    1.54
    Activations Density 0.085%

    No Known Activations