© 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 EvalsExportsinterp-engineNEWAPI 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. 30435
    Prev
    Next
    INDEX
    Explanations

    instances of the term "FE" 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/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
    16
    +0.16
    0.9%
    407
    +0.13
    0.7%
    32
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.16
    0.02
    319
    +0.13
    0.01
    407
    +0.12
    0.01
    Negative Logits
    Ĥ
    -2.03
    ¿½
    -1.83
    Ļª
    -1.82
    ĥ½
    -1.77
    ķ
    -1.70
    ·¸
    -1.67
     same
    -1.66
     vanishing
    -1.65
    ness
    -1.65
     true
    -1.63
    POSITIVE LOGITS
    ATURE
    1.97
    iper
    1.85
    arts
    1.80
    BS
    1.78
    AT
    1.77
    eto
    1.76
    ÅĽci
    1.74
    BP
    1.72
    isty
    1.70
    rench
    1.68
    Activations Density 6.238%

    No Known Activations