© 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. 25506
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intentions or actions directed towards achieving a goal

    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
    103
    +0.15
    0.9%
    427
    +0.15
    0.8%
    434
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.38
    151
    +0.15
    0.31
    434
    +0.12
    0.30
    Negative Logits
    »¿
    -1.97
    Ģ
    -1.81
    ²
    -1.57
    ĸ´
    -1.56
    ĨĴ
    -1.54
    imab
    -1.47
    ¯
    -1.46
    ↵
    -1.44
    ↵↵
    -1.44
    -1.44
    POSITIVE LOGITS
    onic
    1.86
    usions
    1.86
    illes
    1.76
     hydrox
    1.61
    usion
    1.59
     pockets
    1.54
    uding
    1.45
    hip
    1.42
    ampsia
    1.40
    ides
    1.37
    Activations Density 1.629%

    No Known Activations