© 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. 28305
    Prev
    Next
    INDEX
    Explanations

    expressions of strong approval or emphasis

    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
    +0.19
    1.0%
    192
    +0.11
    0.6%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.19
    0.01
    375
    +0.11
    0.01
    257
    +0.11
    0.01
    Negative Logits
    ças
    -1.79
    ·¸
    -1.66
    §
    -1.55
    OLOG
    -1.52
    oste
    -1.50
    imits
    -1.48
    urations
    -1.45
    TO
    -1.43
    ļ
    -1.43
    crib
    -1.43
    POSITIVE LOGITS
    mith
    1.54
    eland
    1.49
     talk
    1.47
     soon
    1.43
    thing
    1.43
    worth
    1.35
     parted
    1.33
     among
    1.32
    illion
    1.30
     nucleus
    1.29
    Activations Density 0.096%

    No Known Activations