© 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. 1-RES-SM
    11. 27152
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    111
    +0.13
    0.8%
    331
    +0.13
    0.8%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.13
    0.09
    281
    +0.13
    0.11
    195
    +0.13
    0.08
    Negative Logits
     psychologists
    -1.74
     finally
    -1.53
     psychiatrist
    -1.51
     doctors
    -1.44
    ********************************
    -1.42
     psychology
    -1.40
     psychologist
    -1.36
    orems
    -1.36
    ologists
    -1.33
    omed
    -1.33
    POSITIVE LOGITS
    »¿
    2.48
    ĨĴ
    1.65
    Īĺ
    1.64
     (@
    1.63
    ↵  âĢĥ
    1.59
    ↵↵↵
    1.59
    1.59
    1.59
    ↵
    1.59
    1.59
    Activations Density 2.629%

    No Known Activations