© 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. 25052
    Prev
    Next
    INDEX
    Explanations

    words that indicate high levels of excitement or intensity

    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
    24
    +0.13
    0.7%
    373
    +0.12
    0.7%
    89
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.05
    18
    +0.12
    0.03
    329
    +0.11
    0.03
    Negative Logits
    že
    -1.62
     accord
    -1.40
     quo
    -1.38
     habitual
    -1.35
     threat
    -1.35
    ('<
    -1.33
    """
    -1.33
    ↵
    -1.33
     underlying
    -1.32
    át
    -1.32
    POSITIVE LOGITS
    iper
    1.78
    acle
    1.59
    ortality
    1.53
    ieg
    1.53
     LICENSE
    1.49
    apple
    1.44
    nee
    1.43
     migrated
    1.42
    jar
    1.38
     always
    1.35
    Activations Density 0.408%

    No Known Activations