© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28797
    Prev
    Next
    INDEX
    Explanations

    the mention of the word "Pr" followed by a number, specifically in the context of processes or products

    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
    156
    +0.15
    0.9%
    350
    +0.14
    0.8%
    203
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.15
    0.03
    172
    +0.14
    0.02
    386
    +0.13
    0.01
    Negative Logits
     generality
    -1.83
    ľĵ
    -1.78
    eri
    -1.72
    ering
    -1.68
    wards
    -1.64
    lla
    -1.60
    shore
    -1.58
     Islands
    -1.57
    eration
    -1.55
    raine
    -1.50
    POSITIVE LOGITS
    imal
    1.75
    ings
    1.72
    inters
    1.71
    incess
    1.62
    inces
    1.60
    iment
    1.57
    inter
    1.49
    ige
    1.48
    uning
    1.48
     aside
    1.48
    Activations Density 0.083%

    No Known Activations