© 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. 26555
    Prev
    Next
    INDEX
    Explanations

    structured elements in legal or 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
    508
    +0.14
    0.8%
    272
    +0.13
    0.7%
    414
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.14
    0.01
    414
    +0.13
    0.01
    272
    +0.12
    0.05
    Negative Logits
     tuned
    -1.59
     resigned
    -1.59
     condemned
    -1.43
     forfe
    -1.41
     said
    -1.35
     mind
    -1.35
     0000000000000000000000000000000000
    -1.34
     formally
    -1.33
    ammar
    -1.31
     opted
    -1.31
    POSITIVE LOGITS
    Ģ
    1.98
    £
    1.96
    ¿
    1.95
    ¾
    1.87
    Ĵ
    1.86
    Ĩ
    1.83
    ³
    1.82
    ĥ½
    1.78
    ĺ
    1.70
    ľĵ
    1.56
    Activations Density 0.528%

    No Known Activations