© 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. 29812
    Prev
    Next
    INDEX
    Explanations

    references to pigs and related terms in agricultural or biological contexts

    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
    156
    +0.23
    1.4%
    321
    +0.17
    1.0%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.23
    0.01
    321
    +0.17
    0.02
    134
    +0.12
    0.02
    Negative Logits
    verting
    -1.54
    âĢł
    -1.50
     correct
    -1.42
    ync
    -1.42
     passing
    -1.38
     faculty
    -1.36
     happening
    -1.34
    MHz
    -1.33
    ferentially
    -1.32
    coming
    -1.32
    POSITIVE LOGITS
    lett
    2.08
    eon
    2.00
    skin
    1.96
    hetti
    1.91
    gy
    1.89
    doms
    1.89
    sty
    1.83
    mentation
    1.82
    lets
    1.80
    let
    1.80
    Activations Density 0.103%

    No Known Activations