© 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. 2-RES-SM
    11. 30605
    Prev
    Next
    INDEX
    Explanations

    the presence of the phrase "distributed under the License."

    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
    412
    +0.14
    0.8%
    198
    +0.13
    0.7%
    499
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.02
    499
    +0.13
    0.02
    157
    +0.12
    0.02
    Negative Logits
    ¨
    -4.70
    ¿½
    -4.64
    ĻĤ
    -4.60
    ĨĴ
    -4.54
    ·¸
    -4.48
    Ĺ
    -4.42
    Ĭ
    -4.42
    ħ
    -4.41
    §
    -4.41
    ķ
    -4.32
    POSITIVE LOGITS
     syll
    1.46
    ÅĽÄĩ
    1.46
    andidate
    1.45
     waiver
    1.45
    ström
    1.43
     edition
    1.40
    ENTIAL
    1.35
    reements
    1.35
     spoken
    1.34
    ERT
    1.34
    Activations Density 0.027%

    No Known Activations