© 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. 28638
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal experiences and reflections

    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
    24
    +0.14
    0.8%
    104
    +0.13
    0.7%
    469
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.12
    331
    +0.13
    0.10
    299
    +0.13
    0.09
    Negative Logits
    Ļª
    -3.22
    ĨĴ
    -3.13
    ĸ
    -3.00
    ĩ
    -2.90
    Ń
    -2.88
    ↵
    -2.84
    -2.84
    -2.84
    -2.84
     ↵
    -2.84
    POSITIVE LOGITS
    nai
    1.59
     really
    1.51
    ipper
    1.42
     subscrib
    1.42
    apan
    1.41
    symbol
    1.36
     treasure
    1.31
    had
    1.29
     ded
    1.29
     might
    1.28
    Activations Density 2.407%

    No Known Activations