© 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. 30983
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to video games and programming concepts

    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
    176
    +0.14
    0.8%
    24
    +0.14
    0.8%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.39
    156
    +0.14
    0.39
    71
    +0.13
    0.38
    Negative Logits
     Rptr
    -1.50
    ↵³³
    -1.46
     AFL
    -1.37
    UTERS
    -1.32
     whom
    -1.30
     could
    -1.29
    ulence
    -1.25
     NAD
    -1.24
    AF
    -1.23
    tees
    -1.22
    POSITIVE LOGITS
     lesson
    1.58
    uler
    1.49
    hesis
    1.44
    adow
    1.40
    pez
    1.39
    nant
    1.39
    ))).
    1.38
    )">
    1.36
    amaz
    1.34
     welcoming
    1.34
    Activations Density 5.695%

    No Known Activations