© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 10983
    Prev
    Next
    INDEX
    Explanations

    references to specific years and events, particularly in relation to actions or feelings of refusal

    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
    +0.20
    1.2%
    121
    +0.14
    0.8%
    279
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.20
    0.04
    279
    +0.14
    0.09
    121
    +0.14
    0.07
    Negative Logits
    ETHOD
    -1.55
    venth
    -1.50
    CPP
    -1.44
     Visual
    -1.31
    ivat
    -1.28
     label
    -1.24
     versa
    -1.24
     vice
    -1.24
     consecutive
    -1.20
     potential
    -1.19
    POSITIVE LOGITS
    fw
    1.51
    zan
    1.51
    omes
    1.49
    falls
    1.48
    gerald
    1.47
    ystems
    1.43
    pha
    1.42
    ctomy
    1.39
    mare
    1.38
    raid
    1.35
    Activations Density 3.833%

    No Known Activations