© 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. 28455
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses

    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
    478
    +0.13
    0.7%
    250
    +0.13
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.13
    0.03
    412
    +0.13
    0.03
    192
    +0.12
    0.02
    Negative Logits
    Ļ
    -3.55
    ®
    -3.35
    ļ
    -3.33
    Ĥ¬
    -3.33
    ´
    -3.31
    ¾
    -3.21
    ħ
    -3.18
    ±
    -3.10
    º
    -3.07
    Ħ
    -3.01
    POSITIVE LOGITS
     certain
    1.66
     hereby
    1.61
     APPEALS
    1.59
     accordance
    1.59
    assed
    1.55
    igate
    1.49
     obey
    1.48
     interrupt
    1.46
     opportun
    1.45
     cooperate
    1.44
    Activations Density 0.100%

    No Known Activations