© 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. 12683
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial matters

    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
    397
    +0.14
    0.7%
    510
    +0.14
    0.7%
    287
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.10
    149
    +0.14
    0.10
    117
    +0.12
    0.11
    Negative Logits
    Ļª
    -3.51
    ķ
    -3.11
    ®
    -2.99
    ¶
    -2.97
    Ĵ
    -2.97
    ¸
    -2.91
    £
    -2.89
    ĺ
    -2.82
    ĭ
    -2.75
    §
    -2.73
    POSITIVE LOGITS
     nor
    5.12
     anymore
    4.90
     whatsoever
    4.50
     anywhere
    3.55
     anything
    3.54
     any
    3.48
    nor
    3.31
     except
    3.27
     unless
    3.10
     yet
    3.09
    Activations Density 2.106%

    No Known Activations