© 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. 2-RES-SM
    11. 28408
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structure

    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
    28
    +0.13
    0.7%
    366
    +0.13
    0.7%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.13
    0.05
    184
    +0.13
    0.04
    28
    +0.12
    0.04
    Negative Logits
    ...](
    -1.62
    ?”
    -1.55
    ?’
    -1.54
    .\
    -1.52
    .’
    -1.52
    inent
    -1.49
    !”
    -1.46
    icals
    -1.46
    .*]{},
    -1.45
    001
    -1.45
    POSITIVE LOGITS
    ²
    2.92
    ·¸
    2.79
    ½
    2.76
    ¾
    2.72
    Ń
    2.65
    Ĥ¬
    2.64
    ĭ
    2.64
    ¿
    2.64
    º
    2.56
    ↵↵
    2.53
    Activations Density 0.150%

    No Known Activations