© 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. 26683
    Prev
    Next
    INDEX
    Explanations

    instances of class definitions in code

    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
    388
    +0.12
    0.7%
    56
    +0.12
    0.6%
    107
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.12
    0.02
    125
    +0.12
    0.02
    456
    +0.11
    0.01
    Negative Logits
    entially
    -1.39
     offset
    -1.38
    imental
    -1.36
    ylene
    -1.36
    MIT
    -1.30
    pendicular
    -1.30
     devil
    -1.25
    liest
    -1.24
     command
    -1.22
     READ
    -1.21
    POSITIVE LOGITS
    viv
    1.75
    elo
    1.69
    ).)
    1.60
    iken
    1.59
    oir
    1.55
    ].)
    1.48
    jury
    1.43
    evo
    1.41
    ialysis
    1.41
    zig
    1.36
    Activations Density 0.071%

    No Known Activations