© 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 EvalsExportsinterp-engineNEWAPI 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. 23513
    Prev
    Next
    INDEX
    Explanations

    elements related to collective responsibility and activism

    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
    111
    +0.65
    7.4%
    156
    +0.64
    7.4%
    425
    +0.06
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.65
    0.03
    442
    +0.64
    0.02
    425
    +0.06
    0.02
    Negative Logits
    ↵↵
    -2.44
    <|outofrange|>
    -2.44
    č↵
    -2.44
    ↵
    -2.44
             ↵
    -2.44
    ↵↵
    -2.44
    ↵
    -2.44
    ↵
    -2.44
    <|outofrange|>
    -2.44
    ↵↵
    -2.44
    POSITIVE LOGITS
    iang
    1.13
    ied
    1.04
    ijer
    1.04
    zzi
    0.97
    enzyme
    0.97
    reb
    0.95
    ching
    0.95
    PING
    0.93
     envy
    0.90
    roscopic
    0.90
    Activations Density 0.034%

    No Known Activations