© 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. 0-MLP-SM
    11. 25369
    Prev
    Next
    INDEX
    Explanations

    words related to stimulation or stimulation-related effects

    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
    317
    +0.15
    0.8%
    184
    +0.14
    0.8%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.01
    111
    +0.14
    0.01
    77
    +0.12
    0.01
    Negative Logits
     latter
    -1.58
     same
    -1.54
    ciparum
    -1.54
    }).$$
    -1.47
    ]>
    -1.42
     courage
    -1.42
    ){#
    -1.42
    iscuss
    -1.38
    }$).
    -1.35
     coast
    -1.35
    POSITIVE LOGITS
    kins
    1.78
    hole
    1.75
    eless
    1.70
    ains
    1.70
    etime
    1.69
    estamp
    1.64
    holes
    1.58
    ¥
    1.57
    ª
    1.56
    Ļ
    1.50
    Activations Density 0.005%

    No Known Activations