© 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. 28763
    Prev
    Next
    INDEX
    Explanations

    references to "board" or related items 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
    156
    +0.22
    1.3%
    113
    +0.12
    0.7%
    256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.22
    0.01
    496
    +0.12
    0.02
    262
    +0.10
    0.01
    Negative Logits
     vain
    -1.71
     certain
    -1.63
    unnumbered
    -1.55
     disturbed
    -1.51
    woke
    -1.49
     conjugation
    -1.49
     deleterious
    -1.47
     sudden
    -1.46
     severe
    -1.46
     '</
    -1.46
    POSITIVE LOGITS
    ists
    2.24
    etry
    2.18
    ist
    2.01
    ettes
    1.94
    atas
    1.88
    holder
    1.86
    writer
    1.81
    istas
    1.81
    isers
    1.81
    works
    1.80
    Activations Density 0.069%

    No Known Activations