© 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. 10452
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating relationships or attributes

    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
    306
    +0.16
    0.9%
    156
    +0.16
    0.9%
    21
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.16
    0.03
    497
    +0.16
    0.01
    306
    +0.16
    0.02
    Negative Logits
    hline
    -1.83
    criptor
    -1.75
    IVE
    -1.66
    ding
    -1.61
    nant
    -1.59
    ient
    -1.54
    lessness
    -1.53
    hip
    -1.53
    CRIPT
    -1.50
    quo
    -1.48
    POSITIVE LOGITS
    ¸
    3.34
    ĸ
    3.24
    ¹
    3.24
    ĵ
    3.19
    ´
    3.19
    ł
    3.14
    »
    3.10
    ĩ
    3.07
    Ł
    3.01
    ¼
    2.98
    Activations Density 0.088%

    No Known Activations