© 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. 14966
    Prev
    Next
    INDEX
    Explanations

    names of celebrities and public figures

    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
    78
    +0.19
    1.2%
    161
    +0.11
    0.7%
    86
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.19
    0.05
    410
    +0.11
    0.06
    271
    +0.11
    0.00
    Negative Logits
    plicity
    -1.27
    consin
    -1.25
    plastic
    -1.25
    treated
    -1.24
    vironment
    -1.23
    iors
    -1.22
    pshire
    -1.21
    sev
    -1.19
    cology
    -1.19
    rept
    -1.18
    POSITIVE LOGITS
    ī
    3.68
    §
    3.42
    İ
    3.39
    «
    3.30
    Ĩ
    3.26
    °
    3.26
    Ī
    3.25
    ·
    3.21
    ¹
    3.20
    ı
    3.17
    Activations Density 0.782%

    No Known Activations