© 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. 27662
    Prev
    Next
    INDEX
    Explanations

    references to detailed technical specifications or figures in a scientific or engineering context

    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
    151
    +0.13
    0.7%
    127
    +0.13
    0.7%
    15
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.13
    0.02
    445
    +0.13
    0.01
    413
    +0.12
    0.01
    Negative Logits
    °
    -1.85
    ¿
    -1.83
    £
    -1.76
    ²
    -1.71
    ¹
    -1.63
     significance
    -1.60
    ¥
    -1.59
    ¿½
    -1.58
    ±
    -1.52
    ¬
    -1.51
    POSITIVE LOGITS
    iom
    1.94
    heets
    1.65
    jer
    1.47
     chi
    1.47
    xe
    1.43
     ribs
    1.39
     (,
    1.39
    rar
    1.38
    epid
    1.36
    orio
    1.36
    Activations Density 0.126%

    No Known Activations