© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 27130
    Prev
    Next
    INDEX
    Explanations

    references to military or armed forces entities and their activities

    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
    484
    +0.12
    0.7%
    138
    +0.12
    0.6%
    110
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.12
    0.11
    31
    +0.12
    0.10
    158
    +0.12
    0.10
    Negative Logits
    holds
    -1.84
    ”:
    -1.81
    fellow
    -1.74
     frames
    -1.53
    ”—
    -1.53
    ”?
    -1.52
    nier
    -1.51
    ctomy
    -1.47
    ]:
    -1.47
    keit
    -1.46
    POSITIVE LOGITS
    ylase
    1.48
     parental
    1.44
     msgid
    1.36
    noreply
    1.33
    orbit
    1.30
    asek
    1.30
     DEBUG
    1.29
    hibernate
    1.28
    rophot
    1.25
     migrate
    1.24
    Activations Density 2.819%

    No Known Activations