© 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. 13144
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and systems

    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
    12
    +0.15
    0.9%
    121
    +0.14
    0.8%
    442
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.15
    0.14
    439
    +0.14
    0.09
    238
    +0.13
    0.08
    Negative Logits
    erved
    -1.56
     precisely
    -1.52
    steine
    -1.44
     exactly
    -1.34
     slowly
    -1.32
     horizontally
    -1.32
     word
    -1.30
     Aid
    -1.30
     ourselves
    -1.29
     isotropic
    -1.28
    POSITIVE LOGITS
    ../../
    1.95
    upon
    1.52
    >=
    1.51
    @
    1.49
     mains
    1.44
    yahoo
    1.41
    ++)
    1.39
    gary
    1.39
    aby
    1.33
    >$
    1.32
    Activations Density 6.252%

    No Known Activations