© 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. 11288
    Prev
    Next
    INDEX
    Explanations

    words related to creativity and artistic expression

    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
    215
    +0.13
    0.7%
    164
    +0.11
    0.6%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    215
    +0.13
    0.03
    498
    +0.11
    0.02
    164
    +0.11
    0.02
    Negative Logits
    apine
    -1.74
    oslav
    -1.73
    heet
    -1.64
    OTO
    -1.53
    OOGLE
    -1.52
    older
    -1.50
    ://
    -1.49
    ail
    -1.42
    Inflater
    -1.38
    iary
    -1.38
    POSITIVE LOGITS
    formance
    1.60
     induct
    1.47
    eps
    1.42
    ©
    1.41
    holders
    1.40
     Ratio
    1.38
     lamb
    1.36
    utions
    1.34
    eping
    1.33
    otype
    1.32
    Activations Density 0.160%

    No Known Activations