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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27737
    Prev
    Next
    INDEX
    Explanations

    references to light or luminosity

    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
    496
    +0.13
    0.7%
    443
    +0.10
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.13
    0.05
    437
    +0.10
    0.03
    381
    +0.10
    0.03
    Negative Logits
    ĻĤ
    -2.18
    ¯
    -2.12
    Į
    -2.03
    ij
    -2.01
    Ľ
    -1.92
    Ŀ
    -1.89
    §
    -1.87
    IJ
    -1.86
     Peninsula
    -1.86
    Ĭ
    -1.85
    POSITIVE LOGITS
    caster
    1.93
    headed
    1.79
    hurst
    1.76
    ening
    1.75
    ened
    1.68
    beam
    1.67
    RO
    1.66
    igt
    1.64
     bulb
    1.62
    emitting
    1.55
    Activations Density 0.024%

    No Known Activations