© 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. 1-RES-SM
    11. 28550
    Prev
    Next
    INDEX
    Explanations

    references to formulas related to various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.18
    1.0%
    172
    +0.13
    0.7%
    269
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.18
    0.01
    177
    +0.13
    0.01
    269
    +0.11
    0.01
    Negative Logits
    ½
    -1.82
    abouts
    -1.76
    OVE
    -1.68
    oves
    -1.56
     sigh
    -1.55
    ]>
    -1.49
    reland
    -1.48
    TON
    -1.46
    Decided
    -1.46
    .’”
    -1.45
    POSITIVE LOGITS
    ic
    2.06
    strings
    1.60
    yers
    1.60
     generator
    1.54
    ière
    1.53
     description
    1.52
     definition
    1.51
     matching
    1.50
    ics
    1.50
    book
    1.49
    Activations Density 0.085%

    No Known Activations