© 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. 28049
    Prev
    Next
    INDEX
    Explanations

    references to specific dates

    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
    82
    +0.13
    0.7%
    373
    +0.11
    0.6%
    77
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.02
    373
    +0.11
    0.02
    374
    +0.10
    0.01
    Negative Logits
    ½
    -2.54
    Ŀ
    -2.47
    ¹
    -2.40
    Ĺ
    -2.31
    ³
    -2.30
    ¼
    -2.28
    °
    -2.20
    ¶
    -2.20
    ĸ
    -2.17
    ģ
    -2.15
    POSITIVE LOGITS
    avel
    1.73
    nel
    1.71
    nai
    1.68
    nbsp
    1.64
     deadline
    1.60
    iston
    1.57
    stein
    1.53
    inian
    1.52
    berry
    1.51
    hew
    1.50
    Activations Density 0.035%

    No Known Activations