© 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. 32044
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to data management

    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
    47
    +0.21
    1.2%
    153
    +0.12
    0.7%
    486
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.21
    0.13
    56
    +0.12
    -0.03
    149
    +0.12
    0.08
    Negative Logits
     contribution
    -1.65
     Vietnamese
    -1.59
     puzzle
    -1.54
     girls
    -1.44
     Afghan
    -1.39
     president
    -1.38
    spoken
    -1.37
    ":"
    -1.34
     how
    -1.34
     fuss
    -1.34
    POSITIVE LOGITS
    erent
    1.89
    uspended
    1.64
    osomes
    1.63
    ubot
    1.62
    usp
    1.61
    resis
    1.60
    nai
    1.56
    icles
    1.56
    jp
    1.54
     periphery
    1.49
    Activations Density 2.623%

    No Known Activations