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. 29115
    Prev
    Next
    INDEX
    Explanations

    sentences that state facts or assertions

    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
    23
    +0.17
    1.0%
    478
    +0.14
    0.8%
    212
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.06
    212
    +0.14
    0.05
    304
    +0.12
    0.04
    Negative Logits
    ĭ
    -4.70
    ģ
    -4.69
    Ļª
    -4.68
    »¿
    -4.47
    Īĺ
    -4.44
    į
    -4.36
    Ĥ¬
    -4.33
    İ
    -4.26
    Ģ
    -4.23
    ī
    -4.23
    POSITIVE LOGITS
     yours
    2.03
     hers
    2.00
     imperative
    1.82
     ours
    1.79
     our
    1.69
    APTER
    1.62
     my
    1.58
     an
    1.55
     Cookie
    1.41
     doubly
    1.39
    Activations Density 0.302%

    No Known Activations