© 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. 1-RES-SM
    11. 29327
    Prev
    Next
    INDEX
    Explanations

    references to environmental policies and their implications

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    17
    +0.21
    1.2%
    156
    +0.19
    1.1%
    392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.21
    0.02
    201
    +0.19
    0.13
    156
    +0.12
    0.17
    Negative Logits
    ETHOD
    -1.69
    ald
    -1.49
     ethical
    -1.41
    odox
    -1.40
    ahoma
    -1.40
    php
    -1.34
     septic
    -1.33
    ocre
    -1.33
     motivated
    -1.31
    bard
    -1.29
    POSITIVE LOGITS
    ĭ
    3.06
    Ģ
    2.90
    ¦
    2.85
    Ļ
    2.77
    Ĵ
    2.77
    ¼
    2.75
    Ĥ
    2.71
    ¶
    2.67
    Ķ
    2.66
    ®
    2.65
    Activations Density 4.315%

    No Known Activations