© 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. 30029
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ind."

    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
    0.8%
    191
    +0.11
    0.6%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.13
    0.01
    111
    +0.11
    0.01
    191
    +0.11
    0.01
    Negative Logits
    ħ
    -1.77
    Ĥ
    -1.77
    Ĺ
    -1.63
    ĭ
    -1.58
     therein
    -1.57
     thereto
    -1.48
    tern
    -1.48
     there
    -1.43
     true
    -1.42
     around
    -1.42
    POSITIVE LOGITS
    ppo
    1.70
    onents
    1.60
    icolor
    1.59
    ulsions
    1.55
    anish
    1.54
    ressions
    1.52
    ovi
    1.50
    ulators
    1.50
    opan
    1.49
    olecule
    1.47
    Activations Density 0.054%

    No Known Activations