© 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. 30030
    Prev
    Next
    INDEX
    Explanations

    references to time and sequence of events in processes or studies

    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
    156
    +0.32
    1.9%
    47
    +0.20
    1.1%
    7
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.32
    0.03
    459
    +0.20
    0.03
    88
    +0.12
    0.03
    Negative Logits
     credibility
    -1.47
    anse
    -1.46
    stalk
    -1.37
    OUS
    -1.36
    derer
    -1.35
    esses
    -1.34
    opard
    -1.31
    bsite
    -1.29
    ume
    -1.29
     Fighter
    -1.27
    POSITIVE LOGITS
    ĻĤ
    4.67
            ↵
    4.55
    4.55
    4.55
    4.55
    č↵
    4.55
    ↵
    4.55
    č↵
    4.55
    <|outofrange|>
    4.55
    č↵
    4.55
    Activations Density 0.144%

    No Known Activations