© 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. 2-RES-SM
    11. 10472
    Prev
    Next
    INDEX
    Explanations

    references to anti and negative sentiments or attitudes

    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
    +0.14
    0.8%
    186
    +0.12
    0.7%
    489
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.14
    0.01
    42
    +0.12
    0.02
    386
    +0.12
    0.01
    Negative Logits
    OOGLE
    -1.96
     timeout
    -1.52
     precedent
    -1.52
    >`
    -1.52
     concur
    -1.45
    }|^
    -1.45
     Redistributions
    -1.44
    )}}{
    -1.43
     Islands
    -1.42
     hereinafter
    -1.40
    POSITIVE LOGITS
    -$
    1.93
    feit
    1.83
    -
    1.78
    plate
    1.69
    leg
    1.66
    hero
    1.59
    inflammatory
    1.49
    âĢij
    1.47
    bery
    1.46
    nex
    1.45
    Activations Density 0.069%

    No Known Activations