© 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. 27585
    Prev
    Next
    INDEX
    Explanations

    elements related to physical confrontation and competition

    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
    170
    +0.22
    1.3%
    56
    +0.12
    0.7%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.22
    0.13
    287
    +0.12
    0.15
    56
    +0.12
    -0.03
    Negative Logits
    ·¸
    -2.26
    İ
    -1.97
    -1.97
    ↵↵
    -1.97
    <|outofrange|>
    -1.97
    ↵
    -1.97
    č↵
    -1.97
    ↵
    -1.97
    -1.97
    -1.97
    POSITIVE LOGITS
    boards
    1.75
     against
    1.55
    oom
    1.52
    maker
    1.49
    ressor
    1.45
    otte
    1.40
    self
    1.35
    chain
    1.34
     together
    1.34
    odies
    1.33
    Activations Density 3.322%

    No Known Activations