© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27217
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in text

    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
    258
    +0.14
    0.8%
    14
    +0.14
    0.8%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.14
    0.04
    258
    +0.14
    0.04
    487
    +0.11
    0.04
    Negative Logits
    /-/
    -1.71
    oku
    -1.67
    ikipedia
    -1.60
     âĢ¦
    -1.46
     coding
    -1.46
    </
    -1.46
     nets
    -1.45
    ".
    -1.39
     PubMed
    -1.39
    ”.
    -1.36
    POSITIVE LOGITS
    »¿
    2.03
    ½
    1.62
     Bend
    1.58
    ricular
    1.56
     APPEALS
    1.52
     thereof
    1.51
     sincere
    1.51
     counsel
    1.50
    )—
    1.49
     insofar
    1.44
    Activations Density 0.138%

    No Known Activations