© 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. 2-RES-SM
    11. 30184
    Prev
    Next
    INDEX
    Explanations

    references to ascension or elevated states

    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
    26
    +0.13
    0.7%
    164
    +0.13
    0.7%
    269
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.13
    0.03
    26
    +0.13
    0.01
    325
    +0.13
    0.03
    Negative Logits
    doing
    -1.64
     quite
    -1.61
    storm
    -1.61
    itian
    -1.52
    bbing
    -1.49
     much
    -1.47
    fully
    -1.47
    having
    -1.46
     intends
    -1.43
     luck
    -1.42
    POSITIVE LOGITS
    endant
    2.26
     slope
    1.92
     ceil
    1.69
     view
    1.65
    endent
    1.64
     gradient
    1.59
    istar
    1.58
     cliffs
    1.57
     slopes
    1.52
     LIM
    1.49
    Activations Density 0.319%

    No Known Activations