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. 29178
    Prev
    Next
    INDEX
    Explanations

    phrases expressing societal expectations and personal responsibility

    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
    391
    +0.16
    0.9%
    198
    +0.16
    0.9%
    436
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.16
    0.10
    198
    +0.16
    0.09
    326
    +0.13
    0.07
    Negative Logits
    egan
    -1.69
     hereby
    -1.58
    blogger
    -1.46
     owner
    -1.43
     daughter
    -1.40
     subscrib
    -1.40
     refund
    -1.36
    eca
    -1.35
     blog
    -1.35
     jointly
    -1.34
    POSITIVE LOGITS
    bol
    1.67
    orts
    1.62
    knowledge
    1.58
    unity
    1.50
    sek
    1.47
    strength
    1.45
    lat
    1.41
    acet
    1.40
    resolution
    1.39
    bod
    1.38
    Activations Density 2.761%

    No Known Activations