© 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. 29423
    Prev
    Next
    INDEX
    Explanations

    elements or data related to programming structures, particularly focusing on errors or bugs in code and the structure of programming functions

    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
    185
    +0.12
    0.7%
    495
    +0.11
    0.6%
    166
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.12
    -0.02
    153
    +0.11
    0.06
    185
    +0.10
    0.04
    Negative Logits
    aday
    -1.42
    culation
    -1.29
     Nature
    -1.29
    omed
    -1.28
    ometry
    -1.27
    esy
    -1.26
    CK
    -1.25
    acha
    -1.25
     time
    -1.24
     permission
    -1.24
    POSITIVE LOGITS
    ľĵ
    1.82
    ŀ
    1.73
    ¾
    1.52
    holder
    1.50
     fide
    1.41
    ños
    1.40
    ır
    1.38
    ¬
    1.37
    isexual
    1.37
     lesbian
    1.33
    Activations Density 1.290%

    No Known Activations