© 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. 29969
    Prev
    Next
    INDEX
    Explanations

    quantifiers indicating a small quantity or number

    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
    15
    +0.14
    0.8%
    83
    +0.12
    0.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.14
    0.05
    284
    +0.12
    0.04
    118
    +0.12
    0.04
    Negative Logits
     economy
    -1.89
    ral
    -1.85
     itself
    -1.67
    ·
    -1.66
    andom
    -1.66
    rah
    -1.64
    ģ
    -1.50
    econom
    -1.48
     language
    -1.46
     Society
    -1.44
    POSITIVE LOGITS
     dozen
    2.27
     hundred
    2.05
     weeks
    1.95
     thousand
    1.79
     minutes
    1.71
     months
    1.68
    itars
    1.63
     omissions
    1.54
     shots
    1.52
     days
    1.52
    Activations Density 0.149%

    No Known Activations