Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27055
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming constructs related to functions and their parameters

    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
    317
    +0.12
    0.7%
    468
    +0.12
    0.7%
    185
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.11
    468
    +0.12
    0.10
    119
    +0.11
    0.07
    Negative Logits
    «
    -4.81
    ¢
    -4.59
    Īĺ
    -4.47
    ½
    -4.46
    Ĭ
    -4.42
    ģ
    -4.38
    ¨
    -4.36
    Į
    -4.35
    ij
    -4.35
    IJ
    -4.34
    POSITIVE LOGITS
    "}](#
    1.60
    =>
    1.57
    substack
    1.50
    ---|---
    1.48
     abroad
    1.38
    amsfonts
    1.36
    ~~~
    1.36
    license
    1.33
    bp
    1.32
    includes
    1.28
    Activations Density 0.645%

    No Known Activations