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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25195
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" used 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    420
    +0.12
    0.7%
    419
    +0.11
    0.6%
    357
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.12
    0.03
    419
    +0.11
    0.03
    56
    +0.11
    -0.01
    Negative Logits
    opa
    -1.70
    ¾
    -1.68
    °
    -1.67
    IJ
    -1.63
    ·
    -1.51
     era
    -1.49
    ---|
    -1.49
    eration
    -1.44
     forth
    -1.42
    ?",
    -1.42
    POSITIVE LOGITS
    ities
    1.56
     purpose
    1.42
    tin
    1.33
    cut
    1.33
     handful
    1.31
    bred
    1.30
    ités
    1.29
    une
    1.29
     rest
    1.28
    tons
    1.27
    Activations Density 0.820%

    No Known Activations