© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    terms related to dynamic and static states or qualities

    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
    156
    +0.20
    1.1%
    304
    +0.12
    0.7%
    334
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.20
    0.02
    334
    +0.12
    0.02
    29
    +0.12
    0.01
    Negative Logits
    ľĵ
    -1.85
    acco
    -1.65
     convicted
    -1.57
     eligible
    -1.51
    owed
    -1.50
    ĥ
    -1.49
     été
    -1.47
    atto
    -1.46
    insured
    -1.45
    fficient
    -1.42
    POSITIVE LOGITS
    ity
    1.93
    itness
    1.86
    casting
    1.85
    izing
    1.69
    cast
    1.66
     between
    1.65
     casting
    1.59
     programming
    1.58
     ranges
    1.56
    uar
    1.55
    Activations Density 0.081%

    No Known Activations