© 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. 30453
    Prev
    Next
    INDEX
    Explanations

    references to data 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
    295
    +0.12
    0.7%
    365
    +0.12
    0.7%
    372
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.12
    0.04
    361
    +0.12
    0.04
    295
    +0.11
    0.04
    Negative Logits
    soever
    -1.78
    bey
    -1.77
     same
    -1.58
    ance
    -1.58
    swers
    -1.57
     ]
    -1.57
    LLOW
    -1.56
     thou
    -1.53
    )](
    -1.51
    sing
    -1.48
    POSITIVE LOGITS
    frame
    2.08
    GridView
    1.90
    pile
    1.75
    venue
    1.74
    bag
    1.72
    flow
    1.69
    illac
    1.67
    ÃŃst
    1.66
    room
    1.61
    cribed
    1.59
    Activations Density 0.094%

    No Known Activations