© 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 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. 24965
    Prev
    Next
    INDEX
    Explanations

    credentials and qualifications in professional 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
    500
    +0.12
    0.7%
    462
    +0.12
    0.6%
    395
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.12
    0.08
    219
    +0.12
    0.11
    33
    +0.11
    0.09
    Negative Logits
    ior
    -1.87
    endor
    -1.77
    angled
    -1.67
    iour
    -1.58
    iors
    -1.54
    rific
    -1.53
    usp
    -1.50
    ijer
    -1.45
    leep
    -1.44
    ibel
    -1.43
    POSITIVE LOGITS
    ľĵ
    1.93
    »¿
    1.87
    ¼
    1.85
    ↵
    1.85
     ↵
    1.85
    ↵
    1.85
    1.85
              ↵
    1.85
    č↵
    1.85
    ↵↵
    1.85
    Activations Density 2.554%

    No Known Activations