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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 29199
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and monetary values

    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
    410
    +0.18
    1.0%
    140
    +0.14
    0.8%
    501
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.18
    0.01
    140
    +0.14
    0.02
    410
    +0.14
    0.02
    Negative Logits
    ership
    -1.87
    alities
    -1.81
    cgi
    -1.75
     cooker
    -1.73
    hower
    -1.72
    amiento
    -1.68
    ional
    -1.65
     behalf
    -1.64
    gence
    -1.62
    ariat
    -1.60
    POSITIVE LOGITS
    Īĺ
    2.62
    ĩ
    2.54
    ²
    2.42
    ¥
    2.41
    ĨĴ
    2.39
    ¶
    2.38
    Ĥ¬
    2.36
    ı
    2.24
    ī
    2.21
    ¸
    2.13
    Activations Density 0.043%

    No Known Activations