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. 11654
    Prev
    Next
    INDEX
    Explanations

    HTML/XML closing tags in text

    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
    201
    +0.13
    0.7%
    209
    +0.12
    0.7%
    77
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.13
    0.04
    209
    +0.12
    0.04
    39
    +0.11
    0.03
    Negative Logits
    .[]{
    -1.90
    .’”
    -1.66
    .**]{}
    -1.62
    .](
    -1.61
    []{
    -1.57
    enen
    -1.53
    **]{},
    -1.47
    reduc
    -1.47
     ](
    -1.46
    .",
    -1.46
    POSITIVE LOGITS
    ĻĤ
    3.44
    Ľ
    3.43
    ·
    3.39
    Īĺ
    3.35
    ¿
    3.22
    Ĥ¬
    3.22
    <|outofrange|>
    3.19
    ↵Č      
    3.19
    <|outofrange|>
    3.19
                                                 
    3.19
    Activations Density 0.075%

    No Known Activations