© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25277
    Prev
    Next
    INDEX
    Explanations

    patterns involving numerical and special characters

    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
    257
    +0.14
    0.8%
    467
    +0.11
    0.6%
    436
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.14
    -0.00
    436
    +0.11
    0.07
    203
    +0.10
    0.05
    Negative Logits
     blame
    -1.53
     taxi
    -1.39
     glance
    -1.39
    à±ģ
    -1.36
     barriers
    -1.35
     mistake
    -1.34
    óg
    -1.34
    ETHOD
    -1.33
    isa
    -1.33
     cries
    -1.32
    POSITIVE LOGITS
    »¿
    2.02
    ↵
    1.98
    ↵    ↵
    1.98
    ↵  ↵
    1.98
    1.98
    <|outofrange|>
    1.98
    1.98
     ↵
    1.98
    ↵
    1.98
    č↵
    1.98
    Activations Density 0.685%

    No Known Activations