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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11404
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and recycling issues

    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
    +0.21
    1.2%
    182
    +0.10
    0.6%
    505
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.21
    -0.00
    128
    +0.10
    0.01
    361
    +0.10
    0.02
    Negative Logits
     Honor
    -1.62
     infinity
    -1.56
     earnest
    -1.49
     trusted
    -1.41
     dawn
    -1.41
     Advance
    -1.40
     suppose
    -1.38
     ÑĩÑĤо
    -1.34
     HREF
    -1.34
     orgasm
    -1.33
    POSITIVE LOGITS
    ful
    2.23
     disposal
    1.99
    waters
    1.97
    bank
    1.77
    place
    1.69
    water
    1.69
     basket
    1.68
    icular
    1.65
    stre
    1.61
    holder
    1.60
    Activations Density 0.232%

    No Known Activations