© 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. 4-RES-SM
    11. 10371
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of a specific character or entity in a narrative context

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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%
    9
    +0.13
    0.7%
    404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.16
    0.04
    404
    +0.13
    0.02
    477
    +0.11
    0.03
    Negative Logits
    ITION
    -2.01
    ITED
    -1.89
    ation
    -1.79
    eting
    -1.72
    ated
    -1.71
    er
    -1.67
    ÅĽÄĩ
    -1.61
    ppings
    -1.50
    erd
    -1.49
    ctin
    -1.47
    POSITIVE LOGITS
    romycin
    2.17
    iop
    2.10
    romb
    2.02
    reshold
    2.00
    istory
    1.97
    roscopic
    1.89
    ttp
    1.88
    olics
    1.87
    iasis
    1.80
    lete
    1.78
    Activations Density 0.200%

    No Known Activations