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. 2-RES-SM
    6. 29254
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all."

    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
    176
    +0.14
    0.8%
    281
    +0.12
    0.7%
    165
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.14
    0.06
    165
    +0.12
    0.05
    492
    +0.11
    0.06
    Negative Logits
    ¿
    -2.37
    ±
    -1.96
    ŀ
    -1.88
    ¿½
    -1.85
    ¹
    -1.85
    ·
    -1.81
    ´
    -1.76
    ¯
    -1.76
    ©
    -1.66
    gni
    -1.65
    POSITIVE LOGITS
    usions
    2.03
    iances
    1.97
    owed
    1.95
    owing
    1.94
     kinds
    1.89
    uded
    1.85
     sorts
    1.85
    ows
    1.83
    ocation
    1.74
    ograft
    1.74
    Activations Density 0.169%

    No Known Activations