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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14304
    Prev
    Next
    INDEX
    Explanations

    elements related to contractual disputes and legal actions

    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
    307
    +0.41
    3.4%
    306
    +0.36
    3.0%
    348
    +0.31
    2.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.41
    0.13
    447
    +0.36
    0.12
    103
    +0.31
    0.08
    Negative Logits
     backgrounds
    -1.22
     search
    -1.20
     experimental
    -1.10
     Collaboration
    -1.07
     enemies
    -1.07
     xen
    -1.06
     meta
    -1.06
     soil
    -1.05
     LEDs
    -1.05
     immunodef
    -1.04
    POSITIVE LOGITS
    ĥ½
    3.17
    Ļ
    2.87
    ·
    2.78
    ¶
    2.75
    ↵
    2.74
    ↵
    2.74
    ↵↵
    2.74
    2.74
    <|outofrange|>
    2.74
    ↵
    2.74
    Activations Density 1.315%

    No Known Activations