© 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. 10258
    Prev
    Next
    INDEX
    Explanations

    the phrase "AS IS" in the context of software licensing

    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
    74
    +0.12
    0.7%
    337
    +0.12
    0.7%
    57
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.02
    105
    +0.12
    0.02
    57
    +0.11
    0.02
    Negative Logits
    cin
    -1.63
    ectomy
    -1.43
    while
    -1.40
    roma
    -1.36
    mouth
    -1.34
    oses
    -1.33
    affin
    -1.29
    noreply
    -1.28
    woke
    -1.28
    oden
    -1.23
    POSITIVE LOGITS
    NESS
    1.74
     LIABLE
    1.54
    ENTIAL
    1.48
     Industries
    1.45
    GAN
    1.37
     Ø£ÙĨ
    1.32
    IK
    1.31
     WARRANTY
    1.31
    ãĤ£
    1.31
     stip
    1.26
    Activations Density 0.059%

    No Known Activations