© 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. 10695
    Prev
    Next
    INDEX
    Explanations

    references to corporate structures and legal 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/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
    431
    +0.15
    0.9%
    419
    +0.15
    0.8%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.15
    0.11
    431
    +0.15
    0.08
    82
    +0.12
    0.08
    Negative Logits
    lined
    -1.49
    cible
    -1.39
    ¼
    -1.36
    ço
    -1.31
    cin
    -1.31
    iv
    -1.28
     bubble
    -1.28
     rush
    -1.27
     APPE
    -1.27
     cleaner
    -1.26
    POSITIVE LOGITS
    *.*
    1.54
     detriment
    1.49
    *.
    1.45
    itage
    1.44
    __.
    1.39
    aceut
    1.38
     tors
    1.34
    ^.
    1.32
    orea
    1.31
    ^[@
    1.27
    Activations Density 3.964%

    No Known Activations