© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    concepts related to the nature of various subjects or phenomena

    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
    9
    +0.17
    0.9%
    397
    +0.14
    0.8%
    216
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    215
    +0.17
    0.04
    9
    +0.14
    0.03
    352
    +0.11
    0.02
    Negative Logits
    ]>
    -1.71
     Units
    -1.48
     revenues
    -1.41
     capacity
    -1.41
     Duty
    -1.40
     eternity
    -1.40
    capacity
    -1.39
    izumab
    -1.39
     throughput
    -1.37
    ÑģÑĤÑĮ
    -1.36
    POSITIVE LOGITS
    ful
    2.23
    arily
    2.11
    finder
    1.84
    fully
    1.79
    frey
    1.78
    utes
    1.77
     quo
    1.72
    fulness
    1.68
    dess
    1.57
    visiae
    1.54
    Activations Density 0.352%

    No Known Activations