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. 29561
    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
    111
    +0.15
    0.9%
    312
    +0.12
    0.7%
    49
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.15
    0.00
    24
    +0.12
    0.00
    430
    +0.12
    0.00
    Negative Logits
    icles
    -1.67
    rait
    -1.66
    ace
    -1.60
     +=
    -1.58
    kowski
    -1.54
    chitz
    -1.53
    neur
    -1.50
    omen
    -1.48
    itti
    -1.39
    imus
    -1.39
    POSITIVE LOGITS
     FREE
    1.71
    &
    1.50
    iplex
    1.42
    ```
    1.39
    gre
    1.37
    ************************************************************************
    1.37
    LICENSE
    1.34
    &-
    1.34
    help
    1.33
    .\[[@
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.