© 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. 27101
    Prev
    Next
    INDEX
    Explanations

    references to ranches or farms

    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
    44
    +0.12
    0.7%
    228
    +0.12
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.01
    172
    +0.12
    0.01
    56
    +0.11
    0.00
    Negative Logits
     rate
    -1.70
    cept
    -1.56
    comes
    -1.55
     strike
    -1.46
    abouts
    -1.45
     strikes
    -1.41
     sclerosis
    -1.39
    ¡
    -1.39
    oggle
    -1.39
     prognostic
    -1.38
    POSITIVE LOGITS
    ol
    1.77
    "}](#
    1.72
    igan
    1.69
    olia
    1.69
    yard
    1.62
    cloth
    1.58
    anan
    1.51
    olor
    1.50
    olate
    1.48
    esan
    1.48
    Activations Density 0.027%

    No Known Activations