Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27465
    Prev
    Next
    INDEX
    Explanations

    references to hydration or related concepts of water consumption

    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
    33
    +0.13
    0.7%
    111
    +0.11
    0.6%
    460
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.13
    0.01
    450
    +0.11
    0.01
    460
    +0.11
    0.01
    Negative Logits
    akes
    -1.72
     stomach
    -1.54
    nil
    -1.53
    ake
    -1.51
    ocular
    -1.48
     Lesser
    -1.41
    akers
    -1.41
     fois
    -1.40
    acher
    -1.37
    ubot
    -1.37
    POSITIVE LOGITS
    eto
    1.96
    rolog
    1.54
    erals
    1.52
     oath
    1.51
    jdbc
    1.48
    rones
    1.43
    Rptr
    1.43
    casters
    1.43
    eral
    1.42
    enario
    1.41
    Activations Density 0.014%

    No Known Activations