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

    Neuronpedia

    APICircuit 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. 11719
    Prev
    Next
    INDEX
    Explanations

    phrases related to software license permissions and conditions

    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
    171
    +0.12
    0.7%
    349
    +0.11
    0.6%
    192
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.12
    0.01
    57
    +0.11
    0.02
    192
    +0.11
    0.01
    Negative Logits
    ¯
    -2.59
    ľĵ
    -2.23
    ®
    -2.19
    ĨĴ
    -2.16
    Ĥ
    -2.14
    Į
    -2.03
    ¦
    -1.96
    ı
    -1.96
    Ľ
    -1.86
    Ĭ
    -1.83
    POSITIVE LOGITS
    icense
    1.67
     hereby
    1.60
     rights
    1.60
    č
    1.58
     harmless
    1.55
     whom
    1.51
     license
    1.48
    written
    1.48
     Permission
    1.46
     grant
    1.45
    Activations Density 0.138%

    No Known Activations