© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27213
    Prev
    Next
    INDEX
    Explanations

    numerical values or counts related to metrics or statistics

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.21
    1.3%
    271
    +0.15
    0.9%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.21
    0.09
    271
    +0.15
    0.01
    17
    +0.13
    0.04
    Negative Logits
    /#
    -1.83
    ocy
    -1.70
    ique
    -1.58
    ttes
    -1.57
    iques
    -1.55
    ics
    -1.54
    ismo
    -1.53
    ström
    -1.53
    blogger
    -1.51
    ifs
    -1.48
    POSITIVE LOGITS
    »
    3.87
    Ī
    3.78
    ´
    3.67
    ©
    3.59
    Į
    3.49
    °
    3.44
    ·¸
    3.41
    ĥ½
    3.40
    ½
    3.30
    į
    3.29
    Activations Density 0.656%

    No Known Activations