© 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 EvalsExportsinterp-engineNEWAPI 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. 9708
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to emerging technologies and innovations in various fields

    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
    47
    +0.15
    0.9%
    169
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.15
    0.04
    200
    +0.14
    0.05
    464
    +0.14
    0.03
    Negative Logits
    **](#
    -1.87
    :]
    -1.72
    >`
    -1.71
    \]](
    -1.58
    ](
    -1.52
    ↵
    -1.52
    "}\].
    -1.50
    _;
    -1.50
     practice
    -1.49
    )\]
    -1.49
    POSITIVE LOGITS
    ricanes
    1.45
    pless
    1.41
     rather
    1.40
    phy
    1.32
     bulbs
    1.31
    arch
    1.30
     Chemical
    1.27
    acs
    1.27
     or
    1.21
     ceil
    1.21
    Activations Density 1.614%

    No Known Activations