© 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. 28898
    Prev
    Next
    INDEX
    Explanations

    references to volume numbers in publications

    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
    307
    +0.13
    0.7%
    59
    +0.12
    0.7%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.13
    0.02
    59
    +0.12
    0.01
    307
    +0.12
    0.01
    Negative Logits
    osine
    -1.66
     backdrop
    -1.63
    ETHOD
    -1.61
    ){#
    -1.60
     immunos
    -1.59
     colorectal
    -1.53
     thyroid
    -1.43
     expect
    -1.41
     proper
    -1.41
     us
    -1.41
    POSITIVE LOGITS
    ¾
    2.46
    umetric
    2.26
    İ
    2.23
    atility
    2.21
    ¤
    2.20
    ī
    2.20
    atile
    2.15
    ¬
    2.12
    Ĭ
    2.09
    Ĵ
    2.06
    Activations Density 0.104%

    No Known Activations