© 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. 26982
    Prev
    Next
    INDEX
    Explanations

    elements related to registration and introductory processes in online forums or communities

    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
    427
    +0.12
    0.7%
    456
    +0.12
    0.6%
    185
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.12
    0.05
    418
    +0.12
    -0.01
    167
    +0.12
    0.03
    Negative Logits
     respectively
    -1.74
     =&
    -1.47
     hybridization
    -1.45
    emale
    -1.41
     headlines
    -1.39
     yields
    -1.34
     lumin
    -1.34
    acked
    -1.33
    riched
    -1.31
    âĤ
    -1.30
    POSITIVE LOGITS
    ©
    2.17
    ¿½
    2.12
    ĥ½
    2.07
    ¦
    2.05
    Ĵ
    1.85
    §
    1.82
    ²
    1.76
    ĸ
    1.75
    į
    1.74
    ĻĤ
    1.74
    Activations Density 0.886%

    No Known Activations