© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29675
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    320
    +0.17
    1.0%
    248
    +0.14
    0.8%
    508
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.18
    248
    +0.14
    0.10
    320
    +0.13
    0.12
    Negative Logits
     warnings
    -1.42
     wounds
    -1.40
     acceptance
    -1.34
     defects
    -1.34
    burn
    -1.34
     Applications
    -1.34
     inconsistent
    -1.32
    ologia
    -1.31
     Problems
    -1.31
     Shield
    -1.30
    POSITIVE LOGITS
    ~~
    1.60
    :)
    1.58
    া
    1.52
    ')->
    1.51
    wagen
    1.46
    ি
    1.46
    ~.
    1.45
    ~~~~~~~~
    1.41
    ίαÏĤ
    1.41
    wind
    1.38
    Activations Density 5.342%

    No Known Activations