© 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. 10389
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific research and methodologies

    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
    21
    +0.28
    1.7%
    40
    +0.10
    0.6%
    450
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.28
    0.02
    40
    +0.10
    0.03
    450
    +0.10
    0.01
    Negative Logits
     same
    -1.40
     Sheet
    -1.29
     resulting
    -1.27
    resis
    -1.27
     expressed
    -1.25
     accomplished
    -1.23
     displayed
    -1.22
     incorrect
    -1.20
     Sheets
    -1.20
    ninger
    -1.18
    POSITIVE LOGITS
    ŀ
    1.94
    ©
    1.81
    ³
    1.78
    Ĭ
    1.76
    ¶
    1.75
    ģ
    1.74
    ¡
    1.72
    Ĩ
    1.71
    °
    1.66
    ¸
    1.65
    Activations Density 0.051%

    No Known Activations