© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    references to governance and community involvement in policy-making

    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
    186
    +0.17
    1.0%
    159
    +0.17
    1.0%
    313
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.17
    0.07
    159
    +0.17
    0.16
    313
    +0.15
    0.06
    Negative Logits
     Redistributions
    -1.83
     imprint
    -1.53
     :=
    -1.50
    /-
    -1.48
    ibular
    -1.47
    ÑĢÑĥг
    -1.46
    cloth
    -1.44
    ="">
    -1.43
    uria
    -1.38
    ="#
    -1.37
    POSITIVE LOGITS
    ©
    3.54
    IJ
    3.53
    ĸ
    3.50
    Ĥ¬
    3.50
    Ł
    3.37
    ĥ
    3.35
    ¿½
    3.25
    §
    3.25
    ¶
    3.23
    ļ
    3.22
    Activations Density 6.555%

    No Known Activations