© 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. 28524
    Prev
    Next
    INDEX
    Explanations

    technical specifications and identifiers in documents

    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
    +0.27
    1.5%
    39
    +0.13
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.27
    0.09
    23
    +0.13
    0.11
    8
    +0.11
    0.03
    Negative Logits
     expects
    -1.64
     encourages
    -1.53
     worth
    -1.44
     mindset
    -1.42
    wrap
    -1.41
     receives
    -1.41
     dressing
    -1.40
    ILITY
    -1.39
     understands
    -1.34
     clar
    -1.32
    POSITIVE LOGITS
    Ĩ
    2.00
    ¦
    1.94
    Īĺ
    1.91
    ¯
    1.87
    ¸
    1.86
    ¿
    1.86
    ł
    1.85
    °
    1.84
    Ŀ
    1.81
    «
    1.77
    Activations Density 1.972%

    No Known Activations