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

    Neuronpedia

    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. MLP Post
    9. 2-MLP-SM
    11. 26829
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court appeals

    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
    363
    +0.17
    1.0%
    63
    +0.10
    0.6%
    357
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.17
    0.02
    372
    +0.10
    0.01
    218
    +0.10
    0.01
    Negative Logits
     business
    -1.56
     judicial
    -1.49
    olit
    -1.44
     property
    -1.43
    amation
    -1.43
    quel
    -1.42
    plicity
    -1.42
     sale
    -1.37
    imab
    -1.36
     legacy
    -1.35
    POSITIVE LOGITS
    ¤
    1.87
    thems
    1.54
     yourself
    1.52
     repeatedly
    1.49
    umble
    1.47
    IENT
    1.38
    ...'
    1.37
    TRY
    1.35
    WHERE
    1.35
    :_
    1.33
    Activations Density 0.150%

    No Known Activations