© 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. 27425
    Prev
    Next
    INDEX
    Explanations

    names and phrases related to specific individuals and their roles or attributes

    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
    507
    +0.12
    0.7%
    108
    +0.12
    0.7%
    310
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.02
    310
    +0.12
    0.07
    191
    +0.12
    0.08
    Negative Logits
     inactivated
    -1.74
    ostatic
    -1.70
    clock
    -1.51
     MORE
    -1.49
    HT
    -1.45
     WARRANTY
    -1.38
    ationally
    -1.37
     ourselves
    -1.37
    OUBLE
    -1.37
     CRT
    -1.33
    POSITIVE LOGITS
    ski
    2.16
    aceae
    1.95
    oulos
    1.83
    ugu
    1.64
    keit
    1.57
    ska
    1.56
     deputies
    1.53
    @
    1.53
     son
    1.48
     District
    1.47
    Activations Density 0.867%

    No Known Activations