© 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. 12741
    Prev
    Next
    INDEX
    Explanations

    references to commercial and industrial contexts

    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
    156
    +0.20
    1.2%
    411
    +0.15
    0.9%
    208
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.20
    0.04
    186
    +0.15
    0.03
    309
    +0.12
    0.04
    Negative Logits
     msgid
    -1.98
    oning
    -1.74
     aloud
    -1.55
    ings
    -1.55
    елÑĮ
    -1.51
    ãģ¾ãģĽ
    -1.49
    аÑĤÑĮ
    -1.47
    ÙĦÙī
    -1.46
    Ñĥк
    -1.45
    олÑĮко
    -1.44
    POSITIVE LOGITS
    ized
    3.30
    ization
    3.17
    isation
    3.03
    ised
    2.99
    izing
    2.59
     establishments
    2.58
    ising
    2.41
    isations
    2.37
    izations
    2.36
    izes
    2.25
    Activations Density 0.241%

    No Known Activations