© 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. 28968
    Prev
    Next
    INDEX
    Explanations

    the presence of specific words or phrases that signify inclusion or reference to examples

    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
    327
    +0.12
    0.7%
    257
    +0.11
    0.6%
    81
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.12
    0.01
    394
    +0.11
    0.01
    35
    +0.11
    0.01
    Negative Logits
    ctions
    -1.62
    jour
    -1.58
    aries
    -1.53
    initions
    -1.46
    iplinary
    -1.44
    lined
    -1.42
    inations
    -1.42
    ossier
    -1.40
    bags
    -1.36
    elta
    -1.36
    POSITIVE LOGITS
    heter
    1.51
    aldehyde
    1.45
     Is
    1.43
    asan
    1.41
    mount
    1.38
    same
    1.36
    dere
    1.32
    fat
    1.32
    moderate
    1.27
     Was
    1.27
    Activations Density 0.013%

    No Known Activations