© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or entities

    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
    +0.14
    0.8%
    397
    +0.12
    0.7%
    152
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.14
    0.06
    78
    +0.12
    -0.00
    21
    +0.11
    0.03
    Negative Logits
    ament
    -1.39
     Wid
    -1.34
    rien
    -1.27
     arsenal
    -1.21
    out
    -1.21
    ored
    -1.20
     Walt
    -1.20
     Ut
    -1.20
     Wed
    -1.19
     analyzer
    -1.19
    POSITIVE LOGITS
    c
    2.64
     c
    2.59
    CA
    2.56
    ca
    2.54
     County
    2.52
     CA
    2.48
    County
    2.31
    ²
    2.28
    ½
    2.13
    µ
    2.13
    Activations Density 0.796%

    No Known Activations