© 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. 25777
    Prev
    Next
    INDEX
    Explanations

    concepts related to comfort and comfortability in various 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/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
    156
    +0.22
    1.3%
    376
    +0.16
    0.9%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.22
    0.02
    452
    +0.16
    0.02
    349
    +0.13
    0.02
    Negative Logits
    asper
    -1.59
    оÑģ
    -1.35
    ÑĢÑĥ
    -1.31
    ureus
    -1.30
    rog
    -1.25
     Species
    -1.25
     Developer
    -1.24
    *>
    -1.24
    да
    -1.24
    opia
    -1.23
    POSITIVE LOGITS
    edly
    2.03
    "}](#
    2.02
    µ
    1.73
    ously
    1.65
     facing
    1.65
    ¢
    1.64
    acting
    1.60
    ł
    1.59
     gaps
    1.55
    erals
    1.52
    Activations Density 0.022%

    No Known Activations