© 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. 4-RES-SM
    11. 9859
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and approval

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.25
    1.4%
    136
    +0.14
    0.8%
    348
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.25
    0.03
    461
    +0.14
    0.03
    271
    +0.13
    0.00
    Negative Logits
     correctly
    -1.51
    npmjs
    -1.39
    iser
    -1.33
     repair
    -1.27
    isers
    -1.24
     bott
    -1.23
     seat
    -1.23
    ipel
    -1.22
     battery
    -1.22
    eld
    -1.21
    POSITIVE LOGITS
     Redistributions
    2.02
    ĻĤ
    2.00
    1.84
    ^](#
    1.81
    ↵Č
    1.80
    ↵↵↵↵
    1.70
    ↵↵
    1.66
    laughs
    1.65
      ↵
    1.64
    OUT
    1.59
    Activations Density 0.310%

    No Known Activations