© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 24902
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the thickness and texture of materials

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    277
    +0.13
    0.7%
    405
    +0.12
    0.7%
    193
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.04
    434
    +0.12
    0.03
    193
    +0.11
    0.02
    Negative Logits
    ģ
    -2.66
    °
    -2.46
    ²
    -2.43
    Ĥ¬
    -2.35
    ļ
    -2.32
    ¶
    -2.31
    ŀ
    -2.27
    ij
    -2.24
    ¤
    -2.24
    ¬
    -2.22
    POSITIVE LOGITS
    ção
    1.65
    htra
    1.58
    ções
    1.57
    wered
    1.50
    ests
    1.47
    tre
    1.41
    leted
    1.37
     administrative
    1.36
    resses
    1.33
    letes
    1.28
    Activations Density 0.225%

    No Known Activations