© 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. 1-RES-SM
    11. 29501
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and data processing

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    271
    +0.13
    0.7%
    23
    +0.13
    0.7%
    97
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.13
    271
    +0.13
    0.05
    17
    +0.13
    0.09
    Negative Logits
    amycin
    -1.62
    herichia
    -1.58
    ensis
    -1.57
    âĢ¦]
    -1.57
    omonas
    -1.55
     (“
    -1.51
    ostatin
    -1.43
    fax
    -1.43
    ulif
    -1.43
     spokeswoman
    -1.42
    POSITIVE LOGITS
    Ļ
    2.91
    ¦
    2.69
    ¿½
    2.66
    ķ
    2.63
    Īĺ
    2.63
    »
    2.54
    ı
    2.50
    ¥
    2.49
    ·¸
    2.48
    ³
    2.44
    Activations Density 0.478%

    No Known Activations