© 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 EvalsExportsAPI 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. 13361
    Prev
    Next
    INDEX
    Explanations

    fragments related to user settings and configurations

    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
    411
    +0.14
    0.8%
    291
    +0.13
    0.7%
    26
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.03
    17
    +0.13
    0.03
    411
    +0.13
    0.05
    Negative Logits
    ģ
    -3.40
    Ŀ
    -3.36
    º
    -3.33
    ī
    -3.16
    Ļ
    -3.11
    ²
    -3.08
    Īĺ
    -3.04
    ³
    -3.00
    ¤
    -2.98
    £
    -2.98
    POSITIVE LOGITS
     user
    4.17
     User
    3.88
     Users
    3.73
    user
    3.65
     users
    3.63
    User
    3.38
    Users
    3.13
    users
    3.04
     username
    2.74
    USER
    2.65
    Activations Density 0.696%

    No Known Activations