© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31755
    Prev
    Next
    INDEX
    Explanations

    words related to regeneration and collaborative efforts

    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
    386
    +0.15
    0.9%
    148
    +0.14
    0.8%
    203
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.05
    148
    +0.14
    0.02
    181
    +0.13
    0.06
    Negative Logits
    mina
    -1.61
    cdn
    -1.52
    à±ģ
    -1.50
    Bye
    -1.48
    lla
    -1.44
    mania
    -1.44
     Morning
    -1.42
    blank
    -1.38
    blr
    -1.35
     Papers
    -1.34
    POSITIVE LOGITS
    ators
    2.56
    ating
    2.52
    ations
    2.46
    ©
    2.28
    ates
    2.27
    ative
    2.21
    atable
    2.16
    atives
    2.14
    atory
    2.06
    acion
    2.05
    Activations Density 0.469%

    No Known Activations