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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28271
    Prev
    Next
    INDEX
    Explanations

    normalized phrases related to safety and compliance in vehicular 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
    379
    +0.14
    0.8%
    17
    +0.14
    0.8%
    40
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.14
    0.09
    280
    +0.14
    0.05
    326
    +0.14
    0.06
    Negative Logits
    lickr
    -1.57
    $]{};
    -1.38
    $]{}
    -1.38
    à¯ģ
    -1.35
     catalogue
    -1.33
     citation
    -1.32
    boards
    -1.31
    ovir
    -1.31
    ographers
    -1.30
    :&
    -1.30
    POSITIVE LOGITS
    ""
    1.49
    ride
    1.47
    ork
    1.46
    aling
    1.44
     nutrients
    1.42
    uming
    1.36
    erne
    1.36
     altitude
    1.36
    uther
    1.35
    iden
    1.34
    Activations Density 6.151%

    No Known Activations