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. 11670
    Prev
    Next
    INDEX
    Explanations

    references to payment and financial transactions

    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
    263
    +0.21
    1.3%
    153
    +0.19
    1.1%
    17
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.21
    0.09
    263
    +0.19
    0.14
    153
    +0.15
    0.06
    Negative Logits
     aged
    -1.60
    \].
    -1.51
    ophone
    -1.43
     cases
    -1.41
    sciously
    -1.36
     case
    -1.34
    harmonic
    -1.34
     alike
    -1.34
     wenn
    -1.32
    \],
    -1.31
    POSITIVE LOGITS
    ¡
    3.38
    ĨĴ
    3.33
    Īĺ
    3.23
    ĸ´
    3.19
    ²
    3.19
    Ļ
    3.18
    Ķ
    3.13
    ¬
    3.13
    ĺ
    3.12
                       
    3.10
    Activations Density 4.070%

    No Known Activations