© 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 EvalsExportsinterp-engineNEWAPI 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. 24109
    Prev
    Next
    INDEX
    Explanations

    subjects or terms related to emotional states or actions

    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
    116
    +0.13
    0.7%
    77
    +0.11
    0.6%
    382
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.13
    0.02
    77
    +0.11
    0.03
    332
    +0.10
    0.04
    Negative Logits
    ↵↵
    -2.45
    ↵
    -2.45
    ↵↵
    -2.45
    ↵↵
    -2.45
    -2.45
    -2.45
    č↵
    -2.45
     ↵
    -2.45
    ↵
    -2.45
    Â
    -2.45
    POSITIVE LOGITS
    imum
    1.52
    ipped
    1.40
    ervation
    1.37
    ified
    1.36
    ilage
    1.34
    ÑĨи
    1.31
    iatric
    1.28
     Bios
    1.27
    ivir
    1.27
     Tok
    1.26
    Activations Density 0.367%

    No Known Activations