© 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. 11270
    Prev
    Next
    INDEX
    Explanations

    instances of the syllable "itt" across 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
    156
    +0.16
    0.9%
    410
    +0.15
    0.8%
    467
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.06
    477
    +0.15
    0.06
    467
    +0.14
    0.04
    Negative Logits
    ½
    -2.07
    ĵ
    -2.07
    ·¸
    -1.98
    ¸
    -1.97
    ´
    -1.92
    ĭ
    -1.91
    ģ
    -1.89
    ¼
    -1.81
    ĻĤ
    -1.81
              ↵
    -1.80
    POSITIVE LOGITS
    les
    2.89
    leneck
    2.62
    lers
    2.47
    ler
    2.47
    ling
    2.44
    led
    2.38
    iest
    2.37
    iness
    2.36
    lest
    2.32
    enden
    2.21
    Activations Density 0.478%

    No Known Activations