© 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. 23195
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and sentiments

    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
    436
    +0.12
    0.7%
    265
    +0.12
    0.6%
    511
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.12
    0.01
    23
    +0.12
    0.02
    511
    +0.10
    0.02
    Negative Logits
    —.
    -1.46
    ".
    -1.44
    ación
    -1.44
     ().
    -1.44
     representing
    -1.41
    cción
    -1.38
    '.
    -1.37
     alive
    -1.35
     etc
    -1.35
    ña
    -1.34
    POSITIVE LOGITS
    ³
    2.25
    Ł
    2.13
    ±
    2.09
    ·
    2.05
    Ļ
    1.98
    Ļª
    1.89
    º
    1.89
    £
    1.85
    »¿
    1.84
    §
    1.81
    Activations Density 0.276%

    No Known Activations