© 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. 4-RES-SM
    6. 11683
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or amount

    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
    466
    +0.24
    1.5%
    307
    +0.13
    0.8%
    78
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.24
    0.04
    466
    +0.13
    0.05
    152
    +0.12
    0.03
    Negative Logits
     commune
    -1.56
     plex
    -1.56
     slightest
    -1.53
    lasses
    -1.43
    rès
    -1.43
    aphragm
    -1.40
    anium
    -1.37
    untime
    -1.36
    ubicin
    -1.33
    __(
    -1.32
    POSITIVE LOGITS
    ta
    2.11
     of
    2.11
    Ħ
    2.09
    ĭ
    2.00
    ®
    1.96
    ĵ
    1.92
    Ļ
    1.78
    İ
    1.78
    ³
    1.76
     tougher
    1.75
    Activations Density 0.149%

    No Known Activations