© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-SM
    11. 27092
    Prev
    Next
    INDEX
    Explanations

    technical data structures or predefined formats in code

    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
    12
    +0.18
    1.0%
    191
    +0.14
    0.8%
    268
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.18
    0.05
    12
    +0.14
    0.04
    416
    +0.14
    0.04
    Negative Logits
    ī
    -3.35
    ¼
    -3.17
    ħ
    -3.15
    ¿½
    -3.14
    ŀ
    -3.10
    Ī
    -3.09
    §
    -3.03
    Ĩ
    -2.98
    İ
    -2.98
    «
    -2.97
    POSITIVE LOGITS
    ieur
    1.78
    ilized
    1.62
    prot
    1.36
    оÑģÑĤ
    1.34
    ils
    1.34
    von
    1.33
    finder
    1.31
     finer
    1.31
    Ñĭй
    1.31
    aven
    1.30
    Activations Density 0.887%

    No Known Activations