© 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. 27953
    Prev
    Next
    INDEX
    Explanations

    terms related to electromagnetic systems and technologies

    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
    507
    +0.14
    0.8%
    213
    +0.12
    0.6%
    156
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.14
    0.01
    48
    +0.12
    0.01
    389
    +0.12
    0.01
    Negative Logits
    Ĭ
    -2.56
    ľĵ
    -2.35
    »¿
    -2.31
    ĥ½
    -2.15
    ĻĤ
    -2.14
    ½
    -2.14
    ·¸
    -2.11
    ¶
    -2.00
    ¿½
    -1.99
    ³
    -1.95
    POSITIVE LOGITS
    rifying
    2.66
    rically
    2.38
    rical
    2.17
    rons
    2.14
    rified
    2.13
    ror
    2.00
    romagnetic
    1.98
    rification
    1.96
    rophys
    1.95
    rific
    1.94
    Activations Density 0.073%

    No Known Activations