© 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. 28746
    Prev
    Next
    INDEX
    Explanations

    references to legal jurisdictions and case details

    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
    422
    +0.12
    0.7%
    199
    +0.10
    0.6%
    200
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.03
    494
    +0.10
    0.02
    200
    +0.10
    0.02
    Negative Logits
     disciples
    -1.39
     drills
    -1.38
    plify
    -1.36
    Payload
    -1.34
    payload
    -1.34
     airst
    -1.28
     payload
    -1.28
    manship
    -1.28
    EMA
    -1.27
    punk
    -1.26
    POSITIVE LOGITS
    000
    1.73
     supra
    1.69
     subd
    1.54
    ÂĶ
    1.49
    omitempty
    1.47
    Ïģγ
    1.46
     hogy
    1.46
    Ïģί
    1.45
    rå
    1.40
    anc
    1.39
    Activations Density 0.316%

    No Known Activations