© 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. 4-RES-SM
    11. 10974
    Prev
    Next
    INDEX
    Explanations

    repeated usage of the letter 'R' in various contexts

    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
    271
    +0.19
    1.1%
    21
    +0.16
    0.9%
    172
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.19
    0.04
    33
    +0.16
    0.04
    116
    +0.12
    0.04
    Negative Logits
    resis
    -1.80
    ctions
    -1.70
     themselves
    -1.45
     existence
    -1.43
     unexpected
    -1.41
    ques
    -1.41
     itself
    -1.40
    fully
    -1.40
     generality
    -1.39
    ros
    -1.39
    POSITIVE LOGITS
    ĺ
    2.84
    ĵ
    2.40
    IJ
    2.34
    Ģ
    2.33
    Ĵ
    2.26
    ĨĴ
    2.19
    ij
    2.13
    Į
    2.09
    ĥ½
    2.07
    ı
    2.07
    Activations Density 0.060%

    No Known Activations