© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30099
    Prev
    Next
    INDEX
    Explanations

    the concept of "passing" or "passing" exams and tasks

    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
    473
    +0.14
    0.8%
    258
    +0.13
    0.7%
    467
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.14
    0.03
    148
    +0.13
    0.01
    467
    +0.13
    0.02
    Negative Logits
    woke
    -1.90
    ½
    -1.69
    ¸
    -1.63
    oarthritis
    -1.43
    ãģ°
    -1.42
    ´
    -1.38
    ·¸
    -1.37
     Father
    -1.33
    arch
    -1.31
    reviewed
    -1.30
    POSITIVE LOGITS
    ports
    2.09
     away
    2.07
    wd
    1.97
    phrase
    1.80
    engers
    1.76
    ittings
    1.53
    enger
    1.52
    itals
    1.51
    als
    1.50
    uls
    1.50
    Activations Density 0.108%

    No Known Activations