© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30877
    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
    243
    +0.13
    0.7%
    199
    +0.12
    0.6%
    233
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.12
    0.00
    2
    -0.12
    0.00
    Negative Logits
    ¼
    -2.47
    į
    -1.69
    ¹
    -1.69
    Ĥ¬
    -1.65
    ¸
    -1.64
    ¦
    -1.63
    Ī
    -1.62
    itan
    -1.60
     Cinema
    -1.58
    ·
    -1.55
    POSITIVE LOGITS
    aling
    1.72
    .*]{}
    1.72
    .’”
    1.71
    )]{}
    1.62
    .](
    1.61
    .]{}
    1.59
    ]."
    1.58
    .**]{}
    1.58
    *]{}
    1.57
    emptyset
    1.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.