© 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. 26658
    Prev
    Next
    INDEX
    Explanations

    references to specific villages or locations

    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
    410
    +0.14
    0.8%
    200
    +0.13
    0.7%
    424
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.03
    181
    +0.13
    0.02
    200
    +0.12
    0.02
    Negative Logits
    Ń
    -2.20
    ľ
    -2.12
    »¿
    -2.08
    ĥ½
    -2.06
    ↵  ³³³
    -2.05
    -2.05
    <|outofrange|>
    -2.05
    <|outofrange|>
    -2.05
    -2.05
    ↵
    -2.05
    POSITIVE LOGITS
    anova
    1.89
    ings
    1.85
    age
    1.84
    agers
    1.71
    ard
    1.70
    amar
    1.63
    agem
    1.62
    elsen
    1.58
    ains
    1.58
    inyl
    1.57
    Activations Density 0.142%

    No Known Activations