© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and commands

    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
    307
    +0.22
    1.3%
    9
    +0.17
    1.0%
    306
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.22
    0.10
    273
    +0.17
    0.05
    400
    +0.14
    0.04
    Negative Logits
    oretic
    -1.60
    mented
    -1.47
    erad
    -1.46
    lying
    -1.45
    matically
    -1.44
    ener
    -1.42
    balls
    -1.39
    aji
    -1.39
    headed
    -1.38
    ball
    -1.37
    POSITIVE LOGITS
    ĻĤ
    7.11
     ↵
    6.96
    6.96
    <|outofrange|>
    6.96
    6.96
    ↵
    6.96
    č↵
    6.96
    ↵↵
    6.96
    6.96
       ↵
    6.96
    Activations Density 1.197%

    No Known Activations