© 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. 4-RES-SM
    11. 9723
    Prev
    Next
    INDEX
    Explanations

    present participles and gerunds related to various actions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    230
    +0.13
    0.7%
    156
    +0.12
    0.7%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.06
    304
    +0.12
    0.07
    2
    +0.11
    0.05
    Negative Logits
    ↵
    -6.29
    ↵↵
    -6.29
    -6.29
    ↵  Âł
    -6.29
    -6.29
    ↵
    -6.29
    ↵↵
    -6.29
    -6.29
    <|outofrange|>
    -6.29
    -6.29
    POSITIVE LOGITS
     capacity
    2.52
     techniques
    2.49
     capacities
    2.40
     habits
    2.34
     abilities
    2.34
     ability
    2.33
     strategies
    2.29
     purposes
    2.28
    redients
    2.26
     skills
    2.25
    Activations Density 0.881%

    No Known Activations