© 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. 2-RES-SM
    11. 26754
    Prev
    Next
    INDEX
    Explanations

    sentences related to conditional situations and decisions made based on potential outcomes

    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
    384
    +0.13
    0.7%
    260
    +0.13
    0.7%
    186
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.13
    0.09
    384
    +0.13
    0.05
    2
    +0.10
    0.07
    Negative Logits
    ľĵ
    -2.64
    ¿½
    -2.59
    ¾
    -2.39
    ļ
    -2.33
    Ļª
    -2.23
    ij
    -2.22
    Ģ
    -2.17
    Ŀ
    -2.15
    ¢
    -2.13
    Ľ
    -2.11
    POSITIVE LOGITS
     return
    1.64
    haps
    1.63
     judgment
    1.60
     luck
    1.60
     <>
    1.55
    iving
    1.51
    reign
    1.49
     judgement
    1.49
     dire
    1.48
    ase
    1.44
    Activations Density 1.400%

    No Known Activations