© 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. 29511
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial concepts and spatial relationships

    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%
    110
    +0.13
    0.7%
    219
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.22
    0.01
    102
    +0.13
    0.01
    219
    +0.12
    0.01
    Negative Logits
    derer
    -1.45
    aths
    -1.45
    vere
    -1.41
    astern
    -1.41
     transgender
    -1.40
    rian
    -1.37
     arbitrary
    -1.36
    ureus
    -1.35
    athing
    -1.33
    agles
    -1.32
    POSITIVE LOGITS
    ĸ
    2.54
    ¡
    2.39
    Ł
    2.27
    ŀ
    2.20
    ently
    2.09
    ĺ
    2.05
    ¤
    2.05
    Ĺ
    1.89
     pic
    1.83
    ¢
    1.82
    Activations Density 0.077%

    No Known Activations