© 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. 9949
    Prev
    Next
    INDEX
    Explanations

    references to the Roman Empire and its cultural or historical impacts

    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
    182
    +0.12
    0.7%
    225
    +0.12
    0.7%
    357
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.12
    0.02
    168
    +0.12
    0.02
    112
    +0.11
    0.02
    Negative Logits
    asing
    -1.58
    quot
    -1.57
    arily
    -1.48
     actionable
    -1.44
     sudden
    -1.43
     diverse
    -1.41
    ance
    -1.40
    gt
    -1.39
     injured
    -1.38
     random
    -1.36
    POSITIVE LOGITS
    £
    2.47
    esque
    2.43
    ¯
    2.42
     Catholic
    2.29
    ģ
    2.24
    ĸ
    2.21
     Catholics
    2.19
    ¾
    2.16
    ī
    2.13
    Ĥ
    2.10
    Activations Density 0.204%

    No Known Activations