© 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. 25972
    Prev
    Next
    INDEX
    Explanations

    words related to criminal justice terms and technical jargon

    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
    111
    +0.47
    3.2%
    156
    +0.45
    3.1%
    275
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.47
    0.01
    497
    +0.45
    0.00
    18
    +0.10
    0.01
    Negative Logits
    ľ
    -1.95
    ¿
    -1.88
    ĩ
    -1.86
    Ī
    -1.84
    ħ
    -1.64
    ĥ
    -1.61
    ı
    -1.61
    ¬
    -1.58
    ĨĴ
    -1.47
    İ
    -1.47
    POSITIVE LOGITS
    osaurs
    1.47
     blame
    1.39
    itives
    1.31
     (£
    1.25
     if
    1.19
    ulses
    1.18
     din
    1.18
    ags
    1.17
    ards
    1.17
    ipation
    1.14
    Activations Density 0.019%

    No Known Activations