© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    the presence of dialogue or quoted speech in the 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/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
    107
    +0.14
    0.8%
    375
    +0.11
    0.6%
    192
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.14
    0.00
    430
    +0.11
    0.00
    440
    +0.11
    0.00
    Negative Logits
    end
    -1.58
    ened
    -1.53
    endent
    -1.49
    iation
    -1.44
     nothing
    -1.43
    iers
    -1.43
    ends
    -1.42
     Batt
    -1.39
     no
    -1.35
     exposition
    -1.35
    POSITIVE LOGITS
    roma
    1.82
    emerg
    1.53
    GREEK
    1.49
    ®
    1.48
    STAR
    1.45
    mining
    1.45
     BASIS
    1.44
     Spacewatch
    1.44
    IJ
    1.43
    OMN
    1.42
    Activations Density 0.000%

    No Known Activations