© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29220
    Prev
    Next
    INDEX
    Explanations

    the word "am" in various contexts, indicating a focus on self-identification or presence

    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
    396
    +0.11
    0.6%
    241
    +0.10
    0.6%
    108
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.11
    0.04
    97
    +0.10
    0.03
    262
    +0.10
    0.04
    Negative Logits
    ±
    -3.05
    Ļª
    -2.72
    ķ
    -2.64
    Ĩ
    -2.59
    §
    -2.57
    ĵ
    -2.53
    »¿
    -2.53
    ´
    -2.50
    Ń
    -2.49
    Ĭ
    -2.37
    POSITIVE LOGITS
    sterdam
    2.05
    plitudes
    1.92
    documentclass
    1.84
    endment
    1.73
    ário
    1.72
    illion
    1.70
    orphous
    1.67
    eless
    1.66
    istic
    1.64
    endi
    1.58
    Activations Density 2.343%

    No Known Activations