© 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. 12032
    Prev
    Next
    INDEX
    Explanations

    negative phrases or sentiments related to actions and events

    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
    78
    +0.17
    1.0%
    255
    +0.14
    0.8%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.03
    201
    +0.14
    0.03
    491
    +0.12
    0.03
    Negative Logits
     Explorer
    -1.50
     att
    -1.50
     alike
    -1.45
    atic
    -1.43
    atically
    -1.41
     fit
    -1.37
     such
    -1.34
    osa
    -1.29
     fitting
    -1.28
    ilated
    -1.26
    POSITIVE LOGITS
    ³
    2.76
    ¶
    2.73
    ¼
    2.65
    Ĥ
    2.62
    ¾
    2.60
    ¿
    2.55
    »
    2.52
    ·
    2.50
    Ħ
    2.49
    ´
    2.48
    Activations Density 0.124%

    No Known Activations