© 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. 26531
    Prev
    Next
    INDEX
    Explanations

    contexts involving consequences or outcomes related to actions or decisions

    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
    198
    +0.12
    0.7%
    202
    +0.10
    0.6%
    474
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.12
    0.03
    104
    +0.10
    0.02
    475
    +0.10
    0.02
    Negative Logits
    uximab
    -1.78
    ippet
    -1.60
    uclear
    -1.50
    onium
    -1.43
     !==
    -1.43
    ucleotide
    -1.42
    yrus
    -1.36
     exception
    -1.31
    ubicin
    -1.30
     ===
    -1.30
    POSITIVE LOGITS
     Ages
    1.63
     Chapter
    1.55
    arten
    1.50
    ±
    1.50
    bies
    1.47
    ł
    1.45
    bard
    1.43
    ļ
    1.43
    point
    1.41
    etto
    1.40
    Activations Density 0.229%

    No Known Activations