© 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. 13722
    Prev
    Next
    INDEX
    Explanations

    details about community engagement and support initiatives

    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
    365
    +0.13
    0.7%
    410
    +0.12
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.13
    0.02
    315
    +0.12
    0.02
    74
    +0.11
    0.02
    Negative Logits
    .[@
    -1.69
    oretic
    -1.66
    ).[
    -1.63
    ocur
    -1.60
    .',
    -1.48
    olds
    -1.48
     environmental
    -1.46
    )].
    -1.44
    ,’
    -1.40
    PCs
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.20
    ¡
    2.09
    ŀ
    1.94
    º
    1.81
    ©
    1.72
    °
    1.68
     glances
    1.68
     tickets
    1.64
     assistant
    1.61
    ´
    1.60
    Activations Density 0.164%

    No Known Activations