© 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. 28203
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accomplishment or successful outcomes

    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
    +0.23
    1.4%
    156
    +0.21
    1.3%
    148
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.23
    0.01
    340
    +0.21
    0.01
    9
    +0.17
    0.01
    Negative Logits
    liche
    -1.84
    ller
    -1.66
    lichen
    -1.63
    lli
    -1.52
    lla
    -1.42
    ----------------------------------------------------
    -1.39
    stein
    -1.38
    ized
    -1.38
    liver
    -1.38
    ksen
    -1.37
    POSITIVE LOGITS
    ļ
    1.92
    Ļ
    1.86
    Īĺ
    1.83
    ł
    1.71
    ·
    1.69
     objectives
    1.51
    ¾
    1.44
     rid
    1.42
    Ł
    1.40
     border
    1.40
    Activations Density 0.009%

    No Known Activations