© 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 EvalsExportsAPI 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. 25284
    Prev
    Next
    INDEX
    Explanations

    specific brand or place names

    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
    23
    +0.24
    1.5%
    271
    +0.14
    0.8%
    148
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.24
    0.09
    148
    +0.14
    0.09
    478
    +0.13
    0.10
    Negative Logits
    velopment
    -1.79
    liga
    -1.46
     offers
    -1.42
    offs
    -1.41
    ulation
    -1.40
    writer
    -1.37
    holders
    -1.37
    mits
    -1.36
    tion
    -1.35
    ators
    -1.35
    POSITIVE LOGITS
    ĻĤ
    3.52
    ľĵ
    2.68
    ¿½
    2.68
    Īĺ
    2.63
    £
    2.60
    ©
    2.50
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.44
    2.42
    <|outofrange|>
    2.42
    ↵
    2.42
    Activations Density 0.798%

    No Known Activations