© 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. 29940
    Prev
    Next
    INDEX
    Explanations

    affirmative responses or confirmations

    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
    249
    +0.14
    0.8%
    161
    +0.12
    0.7%
    382
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.14
    0.03
    260
    +0.12
    0.02
    382
    +0.12
    0.02
    Negative Logits
    ivities
    -2.05
    ocker
    -1.70
    affin
    -1.65
    obacillus
    -1.61
    ivity
    -1.59
    ally
    -1.48
    oil
    -1.47
     itself
    -1.46
    *]{}.
    -1.45
     (\[
    -1.43
    POSITIVE LOGITS
    terday
    2.96
     luck
    1.87
     yes
    1.60
     ÑĩÑĤо
    1.59
     Yes
    1.55
     sir
    1.52
    given
    1.48
    bler
    1.46
     kidding
    1.46
    refs
    1.45
    Activations Density 0.160%

    No Known Activations