© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28970
    Prev
    Next
    INDEX
    Explanations

    expressions conveying emotional intensity or strong feelings

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    110
    +0.12
    0.7%
    197
    +0.12
    0.7%
    401
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.12
    0.01
    440
    +0.12
    0.00
    338
    +0.12
    0.00
    Negative Logits
     PROFITS
    -1.42
    disambiguation
    -1.42
    football
    -1.42
    Īĺ
    -1.41
    ½
    -1.35
    mog
    -1.35
    IRED
    -1.34
    ¿½
    -1.34
    duced
    -1.33
    fony
    -1.30
    POSITIVE LOGITS
    ties
    1.86
    uminous
    1.76
    shire
    1.62
    orer
    1.59
    itudes
    1.57
     finishing
    1.53
     hours
    1.52
    iment
    1.45
    schen
    1.44
    ancy
    1.43
    Activations Density 0.001%

    No Known Activations