© 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. 4-RES-SM
    11. 11951
    Prev
    Next
    INDEX
    Explanations

    markup language syntax or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML and XML markup syntax, particularly comments and structural tags.

    oai_token-act-pair · claude-4-5-haikuTriggered by @mshivr
    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
    21
    +0.37
    2.4%
    255
    +0.20
    1.3%
    306
    +0.19
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.37
    0.05
    450
    +0.20
    0.03
    255
    +0.19
    -0.02
    Negative Logits
     ↵
    -3.77
    ↵
    -3.77
    č↵
    -3.77
    -3.77
    -3.77
     ↵
    -3.77
    -3.77
    ↵
    -3.77
    ↵
    -3.77
    -3.77
    POSITIVE LOGITS
     =>
    1.54
    č↵
    1.53
    "
    1.48
    ![
    1.48
    ]
    1.47
    ){
    1.46
    âĢĥ
    1.40
    )"
    1.39
    "></
    1.38
    )}{
    1.37
    Activations Density 1.608%

    No Known Activations