© 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. 30618
    Prev
    Next
    INDEX
    Explanations

    references to height

    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
    463
    +0.14
    0.8%
    325
    +0.11
    0.6%
    148
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.02
    463
    +0.11
    0.02
    291
    +0.11
    0.02
    Negative Logits
     hers
    -1.54
    arer
    -1.39
    icable
    -1.35
     theirs
    -1.35
     surface
    -1.33
     abrupt
    -1.33
     Area
    -1.32
     brow
    -1.30
     mice
    -1.30
     Am
    -1.27
    POSITIVE LOGITS
    ł
    2.12
    ²
    1.82
    £
    1.82
    Īĺ
    1.81
    ings
    1.80
    est
    1.76
    Ĵ
    1.76
    ening
    1.76
    estone
    1.75
    ŀ
    1.75
    Activations Density 0.022%

    No Known Activations