© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 12312
    Prev
    Next
    INDEX
    Explanations

    numerical values in various formats

    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
    17
    +0.17
    1.0%
    217
    +0.13
    0.7%
    284
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.17
    0.04
    136
    +0.13
    -0.02
    252
    +0.13
    0.11
    Negative Logits
    ¿½
    -1.82
    pod
    -1.44
    ships
    -1.37
    ?”
    -1.29
    mom
    -1.28
    inform
    -1.28
    brit
    -1.27
     adult
    -1.27
     vitro
    -1.24
    medi
    -1.21
    POSITIVE LOGITS
    aceae
    1.52
    endered
    1.51
     counterpart
    1.46
     \%
    1.42
    essee
    1.40
    ursuant
    1.36
     '\
    1.34
    ÈĽi
    1.31
    OTAL
    1.27
     lovers
    1.27
    Activations Density 2.038%

    No Known Activations