© 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. 4-RES-SM
    11. 10920
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and permissions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.18
    1.1%
    271
    +0.16
    1.0%
    21
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.18
    0.01
    460
    +0.16
    0.01
    27
    +0.15
    0.01
    Negative Logits
    ĥ½
    -1.92
    »¿
    -1.72
    ı
    -1.63
    ľĵ
    -1.58
    ķ
    -1.57
      ↵
    -1.51
    -1.51
    -1.51
    ↵↵
    -1.51
    -1.51
    POSITIVE LOGITS
    "),
    2.28
    ").
    2.24
    ")
    2.18
     ")
    1.82
    ”),
    1.82
    ”)
    1.80
    "].
    1.72
    .")
    1.71
    ")]
    1.69
    ");
    1.67
    Activations Density 0.022%

    No Known Activations