© 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. 2-MLP-SM
    11. 24107
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "ex" in words

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.21
    1.2%
    500
    +0.12
    0.7%
    40
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.21
    0.02
    140
    +0.12
    0.02
    11
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -2.47
    ¿½
    -2.09
    į
    -1.96
    Ī
    -1.70
    ↵
    -1.69
    ↵
    -1.69
    <|outofrange|>
    -1.69
    ↵↵
    -1.69
              ↵
    -1.69
    č↵
    -1.69
    POSITIVE LOGITS
     temperatures
    1.71
     bias
    1.62
     coats
    1.51
    ably
    1.47
     around
    1.44
     temperature
    1.41
     pore
    1.38
    idis
    1.32
     deb
    1.31
     oxygen
    1.30
    Activations Density 0.149%

    No Known Activations