© 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. 10791
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer networking

    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
    156
    +0.16
    0.9%
    277
    +0.12
    0.7%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.16
    0.09
    277
    +0.12
    0.05
    444
    +0.12
    0.14
    Negative Logits
     “[
    -2.56
    idenote
    -2.45
     “
    -2.37
     âĢķ
    -2.18
     «
    -2.17
     ðŁĻĤ
    -2.16
    ’
    -2.13
    ‘
    -1.97
     ([**
    -1.95
     Âĵ
    -1.93
    POSITIVE LOGITS
    ";
    5.32
    "
    5.31
    ".
    5.14
    ",
    5.00
    ")
    4.96
    ."
    4.88
    ()"
    4.71
    ;"
    4.66
    "`
    4.59
    ").
    4.53
    Activations Density 2.948%

    No Known Activations