© 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. 2-RES-SM
    11. 13932
    Prev
    Next
    INDEX
    Explanations

    information related to technology product announcements and updates

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    419
    +0.17
    0.9%
    478
    +0.12
    0.7%
    302
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.17
    0.13
    409
    +0.12
    0.13
    454
    +0.11
    0.05
    Negative Logits
    »¿
    -4.66
    ·¸
    -4.49
    º
    -4.44
    Īĺ
    -4.43
    -4.39
    ↵↵
    -4.39
    ↵
    -4.39
    -4.39
    ↵
    -4.39
    ↵
    -4.39
    POSITIVE LOGITS
     2018
    2.31
     2017
    2.20
     2019
    2.17
     upcoming
    2.08
     showc
    2.07
     2016
    2.06
     upgrades
    2.00
     2020
    1.97
     preview
    1.97
     launch
    1.93
    Activations Density 3.921%

    No Known Activations