© 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. 24461
    Prev
    Next
    INDEX
    Explanations

    references to research articles and recommendations in medical contexts

    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
    320
    +0.12
    0.7%
    495
    +0.12
    0.7%
    48
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.09
    272
    +0.12
    0.10
    118
    +0.10
    0.10
    Negative Logits
    Ļ
    -1.96
    Ł
    -1.95
    Ĺ
    -1.91
    µ
    -1.85
    «
    -1.74
    ª
    -1.70
    ł
    -1.68
    ĸ
    -1.65
    ľ
    -1.59
    ŀ
    -1.57
    POSITIVE LOGITS
    "}](#
    1.76
    essee
    1.58
    ricanes
    1.51
    rification
    1.46
    renthood
    1.44
     housing
    1.44
     Harbor
    1.40
    vehicle
    1.40
     indoors
    1.38
    town
    1.36
    Activations Density 1.890%

    No Known Activations