© 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. 28106
    Prev
    Next
    INDEX
    Explanations

    affirmative statements or declarations

    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
    367
    +0.14
    0.8%
    312
    +0.14
    0.7%
    116
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.14
    0.24
    17
    +0.14
    0.16
    233
    +0.14
    0.17
    Negative Logits
    Ŀ
    -4.19
    Ĥ
    -4.15
    ģ
    -3.97
    Ń
    -3.85
    Ģ
    -3.73
    ļ
    -3.62
    ľ
    -3.58
                  ↵
    -3.57
    ↵
    -3.57
    ↵
    -3.57
    POSITIVE LOGITS
     times
    1.77
    ?",
    1.67
     ";
    1.67
    "?
    1.47
     ".
    1.45
     slides
    1.40
     difficulty
    1.37
     thumb
    1.36
    unnumbered
    1.36
     vomiting
    1.35
    Activations Density 0.696%

    No Known Activations