© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    positive attributes of products and experiences

    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
    327
    +0.16
    0.9%
    243
    +0.12
    0.7%
    161
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.16
    0.12
    268
    +0.12
    0.10
    326
    +0.10
    0.07
    Negative Logits
    ĻĤ
    -5.48
    č↵
    -5.02
    č↵
    -5.02
    -5.02
                  ↵
    -5.02
    ↵
    -5.02
     ↵
    -5.02
    -5.02
    č↵
    -5.02
    č↵
    -5.02
    POSITIVE LOGITS
     enough
    1.87
    ently
    1.67
     but
    1.60
    entially
    1.59
     retard
    1.53
     when
    1.53
     (\>
    1.51
    versible
    1.51
     though
    1.50
    nier
    1.48
    Activations Density 1.078%

    No Known Activations