© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28035
    Prev
    Next
    INDEX
    Explanations

    occurrences of the date "August 10."

    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
    369
    +0.13
    0.7%
    177
    +0.13
    0.7%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.13
    0.02
    263
    +0.13
    0.02
    401
    +0.12
    0.01
    Negative Logits
    ĩ
    -1.56
    ĸ´
    -1.54
    Ķ
    -1.47
     pupp
    -1.46
    »¿
    -1.41
     quo
    -1.39
     someone
    -1.39
     child
    -1.39
     ducks
    -1.39
     relation
    -1.38
    POSITIVE LOGITS
    uet
    2.19
    gie
    2.05
    mented
    2.00
    enos
    1.90
    sburg
    1.84
    mentation
    1.77
    uel
    1.76
    eno
    1.75
    doibase
    1.74
    àµį
    1.74
    Activations Density 0.005%

    No Known Activations