© 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. 9590
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or proper names

    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
    77
    +0.15
    0.8%
    410
    +0.14
    0.8%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.03
    410
    +0.14
    0.07
    338
    +0.12
    0.03
    Negative Logits
    aneous
    -1.72
     deprivation
    -1.50
     differentiation
    -1.46
     responding
    -1.45
     analogues
    -1.45
     satisfaction
    -1.43
     enough
    -1.43
    aneously
    -1.42
    ract
    -1.41
     variations
    -1.40
    POSITIVE LOGITS
    olver
    2.02
    nuts
    1.91
    hed
    1.84
    ings
    1.81
    INST
    1.81
    ½
    1.70
    IDTH
    1.67
    ilee
    1.67
    driver
    1.65
    ·¸
    1.64
    Activations Density 0.486%

    No Known Activations