© 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. 2-RES-SM
    11. 10292
    Prev
    Next
    INDEX
    Explanations

    mentions of licensing or software usage 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
    85
    +0.12
    0.6%
    361
    +0.11
    0.6%
    7
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.12
    0.05
    361
    +0.11
    0.06
    7
    +0.10
    0.03
    Negative Logits
    atically
    -1.57
    cyst
    -1.56
    illion
    -1.55
    onica
    -1.54
    ashes
    -1.53
    thon
    -1.46
    isse
    -1.44
    umerable
    -1.43
    liga
    -1.41
    iph
    -1.39
    POSITIVE LOGITS
    ©
    3.65
    ²
    3.64
    į
    3.62
    IJ
    3.55
    ¿½
    3.55
    ³
    3.53
    ¦
    3.52
    ļ
    3.51
    ł
    3.51
    ĭ
    3.48
    Activations Density 0.199%

    No Known Activations