© 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 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. 10939
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or 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/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
    21
    +0.23
    1.4%
    36
    +0.13
    0.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.23
    0.02
    12
    +0.13
    0.02
    292
    +0.12
    0.02
    Negative Logits
    ypse
    -1.62
     sleeve
    -1.61
     medium
    -1.55
    uximab
    -1.53
     retrieval
    -1.48
    tons
    -1.43
     fingers
    -1.41
    cheon
    -1.40
     pages
    -1.39
     Games
    -1.38
    POSITIVE LOGITS
    Appellant
    1.78
    Appellee
    1.74
    INCLUDING
    1.68
    Appellees
    1.66
    Appellants
    1.65
    ³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³
    1.63
    Č
    1.62
    clearly
    1.60
    ³³³³³³³³³³³³³³³³
    1.58
    upon
    1.57
    Activations Density 0.048%

    No Known Activations