© 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. 28528
    Prev
    Next
    INDEX
    Explanations

    the term "Special" 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
    +0.16
    0.9%
    237
    +0.13
    0.7%
    424
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.16
    0.02
    270
    +0.13
    0.02
    424
    +0.12
    0.02
    Negative Logits
     same
    -1.79
    romy
    -1.55
    oming
    -1.51
    oll
    -1.42
     entire
    -1.42
    odic
    -1.40
    gree
    -1.38
     monot
    -1.37
     sudden
    -1.36
     similar
    -1.36
    POSITIVE LOGITS
    ized
    2.33
    ist
    2.03
    ists
    2.01
    ization
    2.00
    ised
    1.92
    izes
    1.88
    ties
    1.81
    IZE
    1.76
    ignment
    1.75
    IZ
    1.66
    Activations Density 0.096%

    No Known Activations