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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26548
    Prev
    Next
    INDEX
    Explanations

    legal terms related to convictions and sentencing

    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
    156
    +0.18
    1.0%
    497
    +0.13
    0.7%
    392
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.18
    0.10
    277
    +0.13
    0.09
    339
    +0.12
    0.07
    Negative Logits
    ĵ
    -3.75
    ↵
    -3.64
    ↵
    -3.64
    ↵
    -3.64
    č↵
    -3.64
    -3.64
    <|outofrange|>
    -3.64
    -3.64
    -3.64
    ↵
    -3.64
    POSITIVE LOGITS
    lights
    1.63
     journalism
    1.53
     surfactant
    1.43
     cent
    1.43
     CDC
    1.40
     Shore
    1.39
    Cent
    1.38
    ube
    1.38
    BITS
    1.36
     minute
    1.34
    Activations Density 1.498%

    No Known Activations