© 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. 2-MLP-SM
    11. 25831
    Prev
    Next
    INDEX
    Explanations

    expressions of commitment or dedication in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    326
    +0.15
    0.8%
    344
    +0.13
    0.7%
    29
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.15
    0.01
    335
    +0.13
    0.01
    295
    +0.13
    0.01
    Negative Logits
    !),
    -1.48
     finally
    -1.45
    otyping
    -1.44
     artists
    -1.42
     Of
    -1.39
     Written
    -1.39
    __)
    -1.36
     ðŁĻĤ
    -1.36
    kees
    -1.36
    nee
    -1.35
    POSITIVE LOGITS
    Ĺ
    2.55
    »¿
    2.55
    ¿
    2.39
    µ
    2.35
    ¿½
    2.33
    ¡
    2.32
    Ħ
    2.27
    ¤
    2.25
    Ŀ
    2.24
    ¥
    2.23
    Activations Density 0.036%

    No Known Activations