© 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. 26819
    Prev
    Next
    INDEX
    Explanations

    references to academic papers or documents, particularly related to research and publications

    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
    358
    +0.13
    0.8%
    111
    +0.12
    0.7%
    310
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    219
    +0.12
    0.01
    360
    +0.11
    0.01
    Negative Logits
    ľĵ
    -2.47
    ¿½
    -2.46
    ľ
    -2.36
    ©
    -2.28
    ĥ
    -2.27
    ¬
    -2.22
    ¨
    -2.21
    Ĺ
    -2.19
    §
    -2.18
    µ
    -2.12
    POSITIVE LOGITS
    etica
    2.05
    ERTY
    2.03
    wn
    1.84
    buffer
    1.78
    fonts
    1.74
    regn
    1.71
    LED
    1.67
    processor
    1.67
    ets
    1.66
    gren
    1.63
    Activations Density 0.007%

    No Known Activations