© 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. 10412
    Prev
    Next
    INDEX
    Explanations

    references to a wide range of items or categories

    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
    148
    +0.13
    0.7%
    125
    +0.12
    0.6%
    15
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.13
    0.04
    284
    +0.12
    0.03
    118
    +0.12
    0.03
    Negative Logits
    ctrine
    -1.83
     itself
    -1.59
    ounger
    -1.58
    ker
    -1.57
    chter
    -1.52
     forth
    -1.50
    orte
    -1.49
    uler
    -1.44
    emaker
    -1.42
     Driver
    -1.42
    POSITIVE LOGITS
    ↵
    4.11
    <|outofrange|>
    4.11
    ↵
    4.11
    ↵
    4.11
    4.11
    ↵
    4.11
    4.11
    č↵č↵
    4.11
    č↵
    4.11
    4.11
    Activations Density 0.089%

    No Known Activations