© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29733
    Prev
    Next
    INDEX
    Explanations

    phrases related to needs and necessities

    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
    112
    +0.12
    0.7%
    450
    +0.12
    0.7%
    57
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.12
    0.05
    38
    +0.12
    0.04
    117
    +0.12
    0.09
    Negative Logits
    ↵
    -4.42
    -4.42
    ↵↵
    -4.42
    ↵↵
    -4.42
    -4.42
    č↵
    -4.42
     ↵
    -4.42
    -4.42
    -4.42
    č↵č↵
    -4.42
    POSITIVE LOGITS
    chool
    2.34
    ystem
    2.33
    ide
    2.32
    mith
    2.16
    ystems
    2.15
    manship
    2.08
    ustain
    2.07
    quare
    1.99
    chaft
    1.98
    ound
    1.97
    Activations Density 1.334%

    No Known Activations