© 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. 27875
    Prev
    Next
    INDEX
    Explanations

    references to specific Australian locations, particularly Queensland and New South Wales

    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
    156
    +0.19
    1.1%
    71
    +0.18
    1.1%
    182
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.19
    0.01
    182
    +0.18
    0.01
    242
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.40
    Ķ
    -2.33
    ı
    -2.30
    ij
    -2.27
    Ħ
    -2.11
    ±
    -2.06
    ¾
    -2.02
    ľ
    -1.94
    ¸
    -1.93
    °
    -1.87
    POSITIVE LOGITS
    vist
    1.88
    erals
    1.76
    EXPORT
    1.71
    er
    1.67
    àµį
    1.67
    selves
    1.64
    bane
    1.61
    \'
    1.61
    eri
    1.59
    ian
    1.53
    Activations Density 0.009%

    No Known Activations