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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27226
    Prev
    Next
    INDEX
    Explanations

    references to the name "Warren" and "Sanders" in the text

    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
    369
    +0.18
    1.1%
    156
    +0.15
    0.9%
    71
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.01
    379
    +0.15
    0.01
    401
    +0.13
    0.01
    Negative Logits
    ĵ
    -2.34
    ı
    -2.22
    ľ
    -2.10
    Ļ
    -2.03
    Ļª
    -2.02
    »¿
    -2.01
    ĸ
    -1.93
    Ĺ
    -1.92
    Ĩ
    -1.92
    ĸ´
    -1.89
    POSITIVE LOGITS
    fields
    1.97
    shire
    1.93
    igan
    1.82
    ford
    1.65
    bourne
    1.60
    issance
    1.57
    ded
    1.55
    pool
    1.55
    velt
    1.54
    neh
    1.54
    Activations Density 0.020%

    No Known Activations