© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 9812
    Prev
    Next
    INDEX
    Explanations

    technical terms related to environmental and life cycle processes

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    12
    +0.18
    1.1%
    6
    +0.13
    0.8%
    320
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.18
    0.14
    6
    +0.13
    0.11
    508
    +0.13
    0.10
    Negative Logits
    blic
    -1.42
    ouin
    -1.35
    áĢº
    -1.33
     registry
    -1.32
     etc
    -1.31
    ctomy
    -1.31
    cliffe
    -1.30
    =".
    -1.30
     dilution
    -1.27
    ="\
    -1.22
    POSITIVE LOGITS
    °
    1.75
    ĥ½
    1.71
    ij
    1.64
    ¥
    1.62
    ause
    1.62
    ¦
    1.53
    Ŀ
    1.53
    ps
    1.50
    İ
    1.50
    ques
    1.49
    Activations Density 4.266%

    No Known Activations