© 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. 1-RES-SM
    6. 27085
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements and alternatives

    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
    478
    +0.16
    0.9%
    23
    +0.15
    0.8%
    295
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.16
    0.02
    35
    +0.15
    0.01
    266
    +0.11
    0.02
    Negative Logits
     breached
    -1.55
    ium
    -1.54
     moment
    -1.52
     lugar
    -1.51
    ibus
    -1.48
     breach
    -1.42
    arium
    -1.40
     inside
    -1.37
    ģ
    -1.36
    aria
    -1.35
    POSITIVE LOGITS
     hers
    1.84
     ours
    1.66
     theirs
    1.64
    shoot
    1.62
    googleapis
    1.55
    yz
    1.53
    cluding
    1.51
    ETHOD
    1.51
     spouses
    1.44
    ppings
    1.43
    Activations Density 0.240%

    No Known Activations