© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 12348
    Prev
    Next
    INDEX
    Explanations

    terms related to knowledge, skills, and expertise

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    431
    +0.15
    0.8%
    348
    +0.11
    0.6%
    232
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.15
    0.04
    233
    +0.11
    0.02
    158
    +0.11
    0.03
    Negative Logits
    ej
    -1.63
     hereto
    -1.54
    ÃŃa
    -1.51
    ]>
    -1.49
     sexes
    -1.40
    ="'$(
    -1.40
     fancy
    -1.39
     silent
    -1.36
    iator
    -1.34
     Honorable
    -1.31
    POSITIVE LOGITS
    fulness
    2.60
     gained
    2.51
     about
    2.19
    base
    2.14
    lessness
    2.05
    ful
    1.95
     gaps
    1.92
     deficit
    1.89
     acquisition
    1.79
     acquired
    1.78
    Activations Density 0.339%

    No Known Activations