© 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. 30183
    Prev
    Next
    INDEX
    Explanations

    items related to legality and software requirements

    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
    478
    +0.17
    0.9%
    178
    +0.14
    0.8%
    121
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.56
    156
    +0.14
    0.51
    71
    +0.13
    0.48
    Negative Logits
    ķ
    -2.35
    ¸
    -2.32
    ij
    -2.11
    ¬
    -2.03
    ģ
    -2.00
    »¿
    -1.97
    ľ
    -1.97
    ĸ´
    -1.89
    Ĥ¬
    -1.88
    ¥
    -1.86
    POSITIVE LOGITS
    >$
    1.97
    >{
    1.78
     promise
    1.73
    >/
    1.61
    @
    1.55
    =#
    1.49
     fact
    1.48
     nature
    1.47
     cascade
    1.45
    >
    1.40
    Activations Density 3.927%

    No Known Activations