© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28078
    Prev
    Next
    INDEX
    Explanations

    phrases related to software configuration

    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
    376
    +0.25
    1.5%
    156
    +0.24
    1.4%
    217
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.25
    0.01
    244
    +0.24
    0.01
    109
    +0.12
    0.01
    Negative Logits
    rank
    -1.63
    ür
    -1.54
    ---|---
    -1.52
    ASE
    -1.45
    llo
    -1.44
    inner
    -1.40
    rb
    -1.40
    join
    -1.40
    ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    -1.39
    oughton
    -1.37
    POSITIVE LOGITS
    ª
    2.40
    °
    2.30
    £
    2.19
    ¢
    2.18
    ĺ
    2.07
    ł
    2.04
    ĻĤ
    1.98
    ķ
    1.89
    Ĺ
    1.88
    Īĺ
    1.83
    Activations Density 0.012%

    No Known Activations