© 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. 29411
    Prev
    Next
    INDEX
    Explanations

    terms related to classification or organization

    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
    +0.21
    1.2%
    376
    +0.16
    0.9%
    470
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.21
    0.01
    470
    +0.16
    0.01
    359
    +0.13
    0.01
    Negative Logits
     gente
    -1.76
     specified
    -1.43
    woke
    -1.39
    derer
    -1.38
     warmed
    -1.33
     olive
    -1.32
     harder
    -1.30
     least
    -1.30
    dered
    -1.30
     peroxide
    -1.30
    POSITIVE LOGITS
    £
    1.77
    ĻĤ
    1.75
    estion
    1.62
    Ļª
    1.57
    IFF
    1.54
    ¡
    1.49
    idelity
    1.47
    iff
    1.45
    face
    1.42
    ents
    1.42
    Activations Density 0.051%

    No Known Activations