© 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. 29488
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the character 'f'

    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
    369
    +0.19
    1.1%
    377
    +0.16
    0.9%
    209
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.19
    0.04
    209
    +0.16
    0.04
    142
    +0.12
    0.03
    Negative Logits
    ¢
    -2.71
    º
    -2.50
    ±
    -2.40
    °
    -2.36
    ĨĴ
    -2.33
    ¶
    -2.29
    ¼
    -2.25
    ¨
    -2.25
    Ļª
    -2.18
    ĩ
    -2.12
    POSITIVE LOGITS
    aux
    1.85
    licts
    1.65
    erguson
    1.64
    acet
    1.60
    lict
    1.57
    ahren
    1.56
    ructose
    1.56
    inally
    1.55
    äll
    1.52
    ritz
    1.51
    Activations Density 0.081%

    No Known Activations