© 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. 26137
    Prev
    Next
    INDEX
    Explanations

    references to closures or restrictions

    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
    162
    +0.15
    0.8%
    156
    +0.13
    0.7%
    488
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.03
    488
    +0.13
    0.02
    112
    +0.12
    0.02
    Negative Logits
    Ķ
    -2.05
    ŀ
    -2.02
    »¿
    -1.98
    Ļ
    -1.98
    ↵
    -1.96
    ↵
    -1.96
    -1.96
    -1.96
    -1.96
    -1.96
    POSITIVE LOGITS
    bow
    1.74
    ness
    1.56
     throat
    1.55
    neck
    1.52
    bows
    1.52
    bsd
    1.49
    zzle
    1.49
     ourselves
    1.48
    isson
    1.46
    opa
    1.43
    Activations Density 0.115%

    No Known Activations