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. 26733
    Prev
    Next
    INDEX
    Explanations

    the term "initially" used in various contexts

    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
    23
    +0.19
    1.1%
    404
    +0.12
    0.7%
    59
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.19
    0.02
    75
    +0.12
    0.01
    396
    +0.11
    0.01
    Negative Logits
    ®
    -2.15
    Ĭ
    -1.94
    thouse
    -1.88
    14514500
    -1.79
    oin
    -1.76
    ¦
    -1.74
    tee
    -1.71
    ter
    -1.70
    ful
    -1.68
    İ
    -1.67
    POSITIVE LOGITS
     glance
    1.80
     wounded
    1.56
     hospitalized
    1.40
     suicidal
    1.37
     slain
    1.36
     vanishing
    1.36
     detained
    1.36
     arrested
    1.36
     ejected
    1.35
     assail
    1.34
    Activations Density 0.043%

    No Known Activations