© 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. 0-MLP-SM
    11. 28758
    Prev
    Next
    INDEX
    Explanations

    mentions of licenses

    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
    286
    +0.13
    0.7%
    383
    +0.13
    0.7%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.13
    0.02
    286
    +0.13
    0.01
    19
    +0.11
    0.01
    Negative Logits
    upon
    -1.88
     successfully
    -1.73
     abruptly
    -1.73
    uther
    -1.59
    ]{}]{}
    -1.57
    around
    -1.57
     safely
    -1.52
     again
    -1.51
     become
    -1.51
    /+
    -1.51
    POSITIVE LOGITS
    veolar
    1.58
    hetti
    1.54
    ño
    1.54
    ız
    1.50
     ceil
    1.49
    igue
    1.48
     era
    1.45
    ramento
    1.44
    anguage
    1.44
    ptions
    1.44
    Activations Density 0.107%

    No Known Activations