© 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. 27782
    Prev
    Next
    INDEX
    Explanations

    phrases indicating numerical ranges or intervals

    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
    47
    +0.15
    0.8%
    376
    +0.12
    0.6%
    129
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.04
    62
    +0.12
    0.03
    466
    +0.12
    0.03
    Negative Logits
    arily
    -1.67
     ubiquitin
    -1.59
    arity
    -1.38
    proving
    -1.37
    ping
    -1.34
     redistribute
    -1.32
     language
    -1.31
    xi
    -1.31
     bundle
    -1.31
    LET
    -1.30
    POSITIVE LOGITS
    ĻĤ
    2.17
     sexes
    2.11
     ↵
    2.09
    <|outofrange|>
    2.09
     ↵
    2.09
       ↵
    2.09
    ↵
    2.09
    2.09
    2.09
    ↵↵
    2.09
    Activations Density 0.056%

    No Known Activations