© 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. MLP Post
    9. 2-MLP-SM
    11. 24102
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to legal and procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    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
    127
    +0.13
    0.7%
    287
    +0.12
    0.6%
    297
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.14
    335
    +0.12
    0.13
    287
    +0.12
    0.14
    Negative Logits
    pered
    -1.90
    ĻĤ
    -1.67
    ”?
    -1.64
    ?”
    -1.61
    âĢIJ
    -1.58
    ?_
    -1.48
    _(
    -1.44
     whom
    -1.44
     digitally
    -1.44
     thereafter
    -1.42
    POSITIVE LOGITS
    practice
    1.60
    elles
    1.57
     (@
    1.44
    atts
    1.43
    ridges
    1.40
    dern
    1.32
    render
    1.30
    oton
    1.28
     practice
    1.26
    afers
    1.26
    Activations Density 2.604%

    No Known Activations