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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29294
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "mid."

    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
    369
    +0.14
    0.8%
    20
    +0.11
    0.6%
    140
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.14
    0.02
    420
    +0.11
    0.02
    386
    +0.11
    0.01
    Negative Logits
    ftware
    -1.71
    ptions
    -1.64
     subscribe
    -1.60
    Ķ
    -1.51
    uch
    -1.50
    omitempty
    -1.49
     complete
    -1.49
    ĸ
    -1.45
    OURCES
    -1.44
    ccess
    -1.40
    POSITIVE LOGITS
    azol
    2.19
    wick
    2.10
    way
    2.02
    range
    1.88
    fielder
    1.87
    rone
    1.79
    town
    1.76
    stad
    1.76
    ermost
    1.73
    strom
    1.71
    Activations Density 0.045%

    No Known Activations