© 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 EvalsExportsAPI 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. 27399
    Prev
    Next
    INDEX
    Explanations

    references to progress in various contexts

    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
    365
    +0.13
    0.8%
    361
    +0.10
    0.6%
    38
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.13
    0.02
    361
    +0.10
    0.01
    77
    +0.10
    0.02
    Negative Logits
    ycin
    -1.84
    anza
    -1.75
     disrespect
    -1.64
     pity
    -1.60
    vereign
    -1.59
    mina
    -1.58
    than
    -1.54
    ubicin
    -1.53
     spite
    -1.52
    ney
    -1.51
    POSITIVE LOGITS
    grounds
    1.89
    ional
    1.86
     underway
    1.84
    ists
    1.73
     polls
    1.67
    icals
    1.64
     achieved
    1.62
    ground
    1.61
    ICT
    1.58
    ors
    1.56
    Activations Density 0.069%

    No Known Activations