Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26931
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions of indifference or flexibility

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    13
    +0.15
    0.8%
    356
    +0.14
    0.7%
    246
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.15
    0.03
    356
    +0.14
    0.03
    246
    +0.12
    0.03
    Negative Logits
    ught
    -1.70
    ounder
    -1.64
    ffer
    -1.60
    elic
    -1.53
    hof
    -1.49
    ented
    -1.45
    oca
    -1.41
     ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    -1.36
    resis
    -1.36
     Examin
    -1.35
    POSITIVE LOGITS
     else
    2.16
    ively
    1.60
    ifice
    1.58
    innings
    1.57
    manship
    1.48
     msgid
    1.46
     ELSE
    1.45
     happened
    1.44
     GENERATED
    1.42
     Else
    1.39
    Activations Density 0.144%

    No Known Activations