© 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. 30034
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of fish or grazing animal known as "granivores."

    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
    111
    +0.13
    0.7%
    90
    +0.12
    0.7%
    230
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.13
    0.01
    90
    +0.12
    0.01
    111
    +0.12
    0.01
    Negative Logits
     slightest
    -1.67
    awning
    -1.57
    oxacin
    -1.49
    ORM
    -1.49
    LEX
    -1.48
     entire
    -1.45
    heastern
    -1.44
    continued
    -1.39
    ollowing
    -1.39
     SEC
    -1.38
    POSITIVE LOGITS
    Ł
    2.69
    µ
    2.58
    ģ
    2.48
    ©
    2.43
    ł
    2.40
    ¤
    2.34
    ī
    2.26
    ±
    2.23
    ª
    2.20
    ¬
    2.19
    Activations Density 0.032%

    No Known Activations