© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 26828
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative emotions, particularly hate

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    91
    +0.12
    0.7%
    115
    +0.12
    0.7%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.12
    0.02
    455
    +0.12
    0.02
    190
    +0.12
    0.02
    Negative Logits
    TS
    -1.57
    EEK
    -1.52
    SK
    -1.51
    ORE
    -1.47
     limb
    -1.45
    kay
    -1.43
    ES
    -1.43
     Invest
    -1.36
    ELY
    -1.35
    AAAAAAAA
    -1.34
    POSITIVE LOGITS
    ī
    1.98
    ģ
    1.82
    words
    1.81
    fest
    1.80
    craft
    1.76
     songs
    1.75
    °
    1.73
    ĸ
    1.72
    marks
    1.72
    ĩ
    1.71
    Activations Density 0.034%

    No Known Activations