© 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. 11606
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or expressions

    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
    156
    +0.51
    3.2%
    136
    +0.10
    0.7%
    7
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.51
    0.06
    448
    +0.10
    0.07
    203
    +0.09
    0.04
    Negative Logits
    {%
    -1.53
    eful
    -1.23
     HERE
    -1.23
     RFC
    -1.22
     à²
    -1.22
    <%
    -1.19
    imab
    -1.17
    cket
    -1.17
     correctly
    -1.17
     trade
    -1.16
    POSITIVE LOGITS
    esque
    1.91
    induced
    1.89
    treated
    1.83
    mediated
    1.82
    Ĥ
    1.82
    ¼
    1.74
    driven
    1.73
    based
    1.71
    related
    1.69
    Ĩ
    1.64
    Activations Density 0.378%

    No Known Activations