Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11422
    Prev
    Next
    INDEX
    Explanations

    elements of structured business or organizational information

    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
    478
    +0.16
    0.9%
    217
    +0.16
    0.9%
    508
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.16
    0.07
    303
    +0.16
    0.06
    478
    +0.12
    0.01
    Negative Logits
    ERY
    -1.87
    nier
    -1.50
    #'
    -1.49
    £
    -1.48
    à±į
    -1.48
    zheimer
    -1.46
    Ń
    -1.42
    ા
    -1.42
    blr
    -1.40
    ĺ
    -1.37
    POSITIVE LOGITS
     anything
    1.50
     none
    1.48
     anybody
    1.47
     whatever
    1.46
    Office
    1.40
    leans
    1.39
     Unknown
    1.39
    Illustration
    1.35
    none
    1.34
    _>
    1.33
    Activations Density 0.412%

    No Known Activations