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. 29518
    Prev
    Next
    INDEX
    Explanations

    references to digital media platforms and related interactions

    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
    369
    +0.15
    0.9%
    302
    +0.15
    0.9%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.15
    0.11
    77
    +0.15
    0.01
    410
    +0.13
    0.16
    Negative Logits
    "}](#
    -1.98
     âĢķ
    -1.64
    ,'"
    -1.62
    bras
    -1.61
    ,''
    -1.61
    .[@
    -1.60
    zzles
    -1.55
    ,[@
    -1.48
    oretic
    -1.45
    apers
    -1.43
    POSITIVE LOGITS
    ités
    1.40
     colleague
    1.38
    ities
    1.38
    ité
    1.38
    actin
    1.35
     oath
    1.33
    ciliation
    1.32
     Guide
    1.32
     colleagues
    1.31
     Representative
    1.28
    Activations Density 5.532%

    No Known Activations