© 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. 29264
    Prev
    Next
    INDEX
    Explanations

    references to licensing terms and conditions

    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
    283
    +0.13
    0.8%
    449
    +0.13
    0.8%
    277
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.13
    0.02
    283
    +0.13
    0.02
    345
    +0.10
    0.01
    Negative Logits
     Coast
    -1.57
    unnumbered
    -1.54
    LLOW
    -1.52
    around
    -1.48
     hers
    -1.46
     hesitate
    -1.46
    )):
    -1.45
    '));
    -1.44
     neighbor
    -1.42
     see
    -1.40
    POSITIVE LOGITS
    recht
    1.94
    bour
    1.88
    jä
    1.80
    ismus
    1.78
    icense
    1.74
    kowski
    1.74
    liche
    1.67
    ibase
    1.59
    cloth
    1.58
    ivation
    1.57
    Activations Density 0.009%

    No Known Activations