© 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. 25632
    Prev
    Next
    INDEX
    Explanations

    phrases or references to compliance and quality benchmarks 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
    156
    +0.15
    0.9%
    376
    +0.13
    0.8%
    79
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.15
    0.02
    9
    +0.13
    0.02
    209
    +0.13
    0.01
    Negative Logits
    §
    -2.29
    IJ
    -2.02
    Ĵ
    -1.89
    ¥
    -1.89
    ¯
    -1.82
     dreams
    -1.76
     grateful
    -1.67
     gone
    -1.66
    ·¸
    -1.66
     sigh
    -1.62
    POSITIVE LOGITS
    heet
    2.18
    burg
    1.92
    optic
    1.79
    icum
    1.68
    imple
    1.65
    ervation
    1.64
    erv
    1.63
    table
    1.57
    fix
    1.56
    um
    1.55
    Activations Density 1.090%

    No Known Activations