© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 13641
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of."

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    23
    +0.19
    1.1%
    457
    +0.13
    0.8%
    136
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.19
    0.07
    356
    +0.13
    0.06
    237
    +0.13
    0.06
    Negative Logits
    ī
    -1.99
    feld
    -1.72
    stroke
    -1.59
    nier
    -1.58
    chen
    -1.45
    åı·
    -1.44
    GTH
    -1.39
    liness
    -1.36
    etti
    -1.35
    ató
    -1.35
    POSITIVE LOGITS
    ribute
    1.75
     each
    1.65
     both
    1.52
     properly
    1.45
     any
    1.34
     course
    1.34
    ibernate
    1.32
    ).](
    1.31
    ...](
    1.31
    nt
    1.31
    Activations Density 0.475%

    No Known Activations