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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29773
    Prev
    Next
    INDEX
    Explanations

    terms related to construction materials and surfaces

    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
    156
    +0.17
    0.9%
    246
    +0.11
    0.6%
    504
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.17
    0.00
    504
    +0.11
    0.01
    413
    +0.10
    0.01
    Negative Logits
    Ī
    -2.28
    «
    -1.84
    ©
    -1.74
    ī
    -1.74
    ¦
    -1.72
    Į
    -1.70
    Ľ
    -1.68
    Ĩ
    -1.64
    ij
    -1.60
    ired
    -1.57
    POSITIVE LOGITS
     examples
    1.84
     example
    1.78
    mente
    1.64
     faç
    1.61
    faced
    1.57
    bones
    1.54
    velopment
    1.52
    backs
    1.52
    ypse
    1.50
    ulence
    1.49
    Activations Density 0.287%

    No Known Activations