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. 29458
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    56
    +0.13
    0.7%
    249
    +0.13
    0.7%
    350
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.13
    0.00
    2
    -0.11
    0.00
    Negative Logits
    ships
    -1.73
    burgh
    -1.52
    street
    -1.38
     Broadway
    -1.38
     grievances
    -1.38
    wich
    -1.34
    INGS
    -1.34
     history
    -1.34
     expans
    -1.32
    baum
    -1.29
    POSITIVE LOGITS
    mology
    1.64
    ]{}]{}
    1.62
    ati
    1.60
    nat
    1.49
    ini
    1.47
    ]{}\
    1.46
    ]{}
    1.43
    ]{}[
    1.42
    ain
    1.41
    olin
    1.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.