© 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. 28152
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and function definitions

    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
    46
    +0.12
    0.6%
    452
    +0.11
    0.6%
    160
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.12
    -0.04
    167
    +0.11
    0.06
    46
    +0.11
    0.04
    Negative Logits
    ";
    -1.71
    .”
    -1.54
    ”.
    -1.53
    :`
    -1.50
    Ĥ
    -1.49
    ".
    -1.47
    antly
    -1.43
    .";
    -1.41
    "</
    -1.35
    air
    -1.34
    POSITIVE LOGITS
    "}](#
    1.79
    )](#
    1.76
    ))^
    1.59
    ]),
    1.49
    %),
    1.46
    )],
    1.45
    ,)
    1.45
    )),
    1.44
    >&
    1.43
    ),\\
    1.43
    Activations Density 2.973%

    No Known Activations