© 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. 26935
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or notable events involving individuals or entities

    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
    156
    +0.25
    1.4%
    114
    +0.15
    0.8%
    105
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.25
    -0.02
    416
    +0.15
    0.08
    242
    +0.13
    0.10
    Negative Logits
     liter
    -1.55
    ĸ
    -1.52
    burn
    -1.50
    entially
    -1.48
     etc
    -1.47
    aped
    -1.36
    ylvania
    -1.33
     respectively
    -1.33
    Ľ
    -1.31
    ARRAY
    -1.31
    POSITIVE LOGITS
    :</
    1.70
    "?"
    1.66
    :]
    1.47
     shutdown
    1.41
    :\
    1.35
    ]>
    1.32
    ?’
    1.32
    !’
    1.31
    |>
    1.30
     surprising
    1.28
    Activations Density 3.364%

    No Known Activations