© 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. 29695
    Prev
    Next
    INDEX
    Explanations

    mentions of the quantity and types of rooms in a property

    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
    +0.27
    1.6%
    376
    +0.14
    0.9%
    115
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.27
    0.02
    480
    +0.14
    0.01
    235
    +0.13
    0.01
    Negative Logits
     yours
    -1.77
    terest
    -1.65
    ONS
    -1.62
    rians
    -1.61
     APPEALS
    -1.56
    keit
    -1.54
     snow
    -1.54
    tig
    -1.50
    yline
    -1.44
    umbent
    -1.44
    POSITIVE LOGITS
    "}](#
    2.05
    "],
    1.68
    ģ
    1.68
     detail
    1.64
    etting
    1.60
    "].
    1.58
    hell
    1.53
    IER
    1.47
    block
    1.45
    imeter
    1.45
    Activations Density 0.021%

    No Known Activations