© 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. 28248
    Prev
    Next
    INDEX
    Explanations

    instances of eyewitness accounts and descriptions of events

    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
    291
    +0.14
    0.8%
    153
    +0.13
    0.7%
    57
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.09
    291
    +0.13
    0.08
    137
    +0.12
    0.09
    Negative Logits
    ault
    -1.71
     onward
    -1.70
    icile
    -1.69
    bourg
    -1.56
    ters
    -1.48
    aine
    -1.46
     Ltd
    -1.44
     guarant
    -1.40
    ariant
    -1.38
     relies
    -1.38
    POSITIVE LOGITS
    ');
    1.71
    ...](
    1.68
    ']);
    1.60
     plight
    1.57
    ';
    1.53
    .'"
    1.51
    '."
    1.50
    ...'
    1.50
    '];
    1.46
     bite
    1.45
    Activations Density 1.593%

    No Known Activations