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

    Neuronpedia

    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. 2-RES-SM
    11. 10741
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss website usage and privacy-related terms

    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/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
    320
    +0.19
    1.1%
    17
    +0.17
    1.0%
    186
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.19
    0.13
    210
    +0.17
    0.02
    105
    +0.15
    0.10
    Negative Logits
    Į
    -1.69
    bibliography
    -1.69
    ©
    -1.59
     cref
    -1.56
    ischer
    -1.55
    ylan
    -1.47
    Ŀ
    -1.38
    ½
    -1.37
     trademark
    -1.36
    İ
    -1.36
    POSITIVE LOGITS
     land
    1.46
    iably
    1.43
     ourselves
    1.41
    grily
    1.38
     warp
    1.38
    mie
    1.37
     ?
    1.37
    perate
    1.36
     lands
    1.36
     crops
    1.35
    Activations Density 3.809%

    No Known Activations