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. 12007
    Prev
    Next
    INDEX
    Explanations

    terms related to academic and cultural topics, specifically around essays and research in various contexts

    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
    271
    +0.19
    1.1%
    478
    +0.11
    0.6%
    291
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.21
    156
    +0.11
    0.25
    71
    +0.11
    0.21
    Negative Logits
     Suit
    -1.82
     Approach
    -1.65
     Fifth
    -1.61
     Station
    -1.58
     Field
    -1.57
     Generation
    -1.54
     Stadium
    -1.51
     themselves
    -1.51
     First
    -1.49
    ulating
    -1.49
    POSITIVE LOGITS
    Ĺ
    3.09
    Īĺ
    2.91
    ĻĤ
    2.69
    ²
    2.67
    ĨĴ
    2.66
    ģ
    2.66
    »¿
    2.64
    ³
    2.62
    Ń
    2.61
    ¿½
    2.59
    Activations Density 7.190%

    No Known Activations