© 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. 4-RES-SM
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    negative or prohibitive language related to commands or instructions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.38
    2.3%
    78
    +0.19
    1.1%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.38
    0.06
    203
    +0.19
    0.05
    448
    +0.12
    0.07
    Negative Logits
    umab
    -1.58
    ailed
    -1.43
     Motion
    -1.37
     Disorder
    -1.36
    arians
    -1.33
    bital
    -1.32
    fered
    -1.31
     Field
    -1.30
     disorder
    -1.26
     Register
    -1.22
    POSITIVE LOGITS
    Ĥ
    3.57
    Ķ
    3.55
    ĸ
    3.47
    ®
    3.43
    ¾
    3.42
    °
    3.38
    Ĩ
    3.37
    ½
    3.36
    ĨĴ
    3.34
    ¥
    3.28
    Activations Density 0.429%

    No Known Activations