© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 10946
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court documents

    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
    419
    +0.13
    0.7%
    12
    +0.11
    0.6%
    85
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.13
    0.03
    391
    +0.11
    0.03
    21
    +0.11
    0.03
    Negative Logits
     nothing
    -1.49
     terminals
    -1.44
     95
    -1.40
     maximizing
    -1.38
    ^{+
    -1.37
     vain
    -1.31
     favor
    -1.31
    pressing
    -1.30
     recycling
    -1.28
     conditioned
    -1.25
    POSITIVE LOGITS
    isch
    1.60
     backdrop
    1.52
    iary
    1.47
    sein
    1.37
    qua
    1.37
     curiam
    1.36
    District
    1.34
    blogspot
    1.31
    ichael
    1.30
    ischen
    1.29
    Activations Density 0.315%

    No Known Activations