© 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 EvalsExportsinterp-engineNEWAPI 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. 13142
    Prev
    Next
    INDEX
    Explanations

    library-related terms and expressions

    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
    53
    +0.14
    0.8%
    410
    +0.14
    0.8%
    354
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.14
    0.02
    445
    +0.14
    0.01
    410
    +0.14
    0.02
    Negative Logits
    ickness
    -1.69
    iasis
    -1.64
    +}
    -1.57
     younger
    -1.51
    enron
    -1.49
     appearance
    -1.46
     departure
    -1.44
    around
    -1.43
     contrast
    -1.40
    thood
    -1.38
    POSITIVE LOGITS
    Ģ
    2.88
    ¾
    2.76
    ģ
    2.57
    ¿½
    2.54
    ®
    2.52
    ĻĤ
    2.49
    ħ
    2.42
    °
    2.37
    ¶
    2.35
    ¦
    2.34
    Activations Density 0.107%

    No Known Activations