© 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. 0-MLP-SM
    11. 26249
    Prev
    Next
    INDEX
    Explanations

    terms associated with urgency or urgent situations

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.11
    0.6%
    191
    +0.10
    0.6%
    7
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.11
    0.01
    465
    +0.10
    0.01
    70
    +0.10
    0.01
    Negative Logits
    tern
    -1.90
    ching
    -1.75
    ables
    -1.59
     subsequently
    -1.57
     accord
    -1.51
     previously
    -1.50
     sag
    -1.47
    cess
    -1.44
     desired
    -1.41
     href
    -1.40
    POSITIVE LOGITS
    iator
    1.78
    enstein
    1.66
    ycin
    1.63
    iom
    1.57
    iates
    1.53
    inia
    1.50
    idity
    1.47
    FW
    1.45
    yc
    1.44
    ISPR
    1.40
    Activations Density 0.013%

    No Known Activations