© 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. 30733
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Free" in relation to software and licenses

    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
    +0.17
    1.0%
    349
    +0.11
    0.6%
    98
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.17
    0.02
    349
    +0.11
    0.02
    253
    +0.10
    0.01
    Negative Logits
    ľĵ
    -2.24
    ĨĴ
    -1.95
    Ĺ
    -1.92
    ĻĤ
    -1.81
    ĵ
    -1.73
    ...)
    -1.68
    Ł
    -1.68
    Ķ
    -1.63
    ĺ
    -1.62
    plasia
    -1.62
    POSITIVE LOGITS
    bsd
    2.02
     Software
    1.84
    BSD
    1.69
     Computing
    1.65
     WARRANTY
    1.63
     Intel
    1.60
     Energy
    1.56
     Financial
    1.55
    bie
    1.53
     State
    1.53
    Activations Density 0.023%

    No Known Activations