© 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. 11370
    Prev
    Next
    INDEX
    Explanations

    instances of the word "despite" indicating contrast or adversity

    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
    465
    +0.13
    0.7%
    274
    +0.13
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.13
    0.04
    274
    +0.13
    0.03
    239
    +0.11
    0.03
    Negative Logits
    inos
    -1.70
    ģ
    -1.52
     into
    -1.47
    ħ
    -1.47
     Biosystems
    -1.45
    Ļ
    -1.39
    aurus
    -1.39
    §
    -1.30
    onic
    -1.29
    anse
    -1.28
    POSITIVE LOGITS
    drawn
    1.76
     previous
    1.59
     luck
    1.58
    placement
    1.57
     hers
    1.54
    throws
    1.46
    wise
    1.45
    noon
    1.43
    birth
    1.43
    placing
    1.41
    Activations Density 0.227%

    No Known Activations