© 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. 27730
    Prev
    Next
    INDEX
    Explanations

    terms related to software licenses and distribution

    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
    323
    +0.17
    1.0%
    214
    +0.12
    0.7%
    398
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.17
    0.02
    79
    +0.12
    0.01
    464
    +0.10
    0.02
    Negative Logits
    ¯
    -2.80
    ²
    -2.30
    ¢
    -2.29
    °
    -2.19
    ±
    -2.17
    §
    -2.13
    ¿
    -2.11
    ¦
    -2.11
    ®
    -2.08
    ½
    -2.06
    POSITIVE LOGITS
    aho
    1.44
     BACKGROUND
    1.41
    rika
    1.40
     lar
    1.38
    ól
    1.34
    stro
    1.33
    éri
    1.31
    bars
    1.31
    itution
    1.28
     classes
    1.27
    Activations Density 0.116%

    No Known Activations