© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    legal citation formats and procedural references within legal documents

    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
    +0.14
    0.8%
    469
    +0.13
    0.7%
    126
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.14
    -0.00
    255
    +0.13
    -0.00
    0
    +0.12
    0.02
    Negative Logits
    igraph
    -1.72
    eno
    -1.63
    ipore
    -1.57
    '):
    -1.55
    eter
    -1.51
    aille
    -1.48
    iser
    -1.48
     themselves
    -1.40
    er
    -1.39
     such
    -1.39
    POSITIVE LOGITS
    ties
    1.75
    Č
    1.44
    NESS
    1.43
    laughs
    1.41
    1.38
     Honorable
    1.37
    1.36
     FITNESS
    1.35
    isms
    1.34
     False
    1.31
    Activations Density 0.065%

    No Known Activations