© 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. 29525
    Prev
    Next
    INDEX
    Explanations

    references to collective human experiences or sentiments

    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
    87
    +0.12
    0.7%
    466
    +0.12
    0.7%
    419
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.12
    0.01
    419
    +0.12
    0.01
    249
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.19
    ?**
    -1.95
    ?_
    -1.78
    ?"
    -1.77
    ounder
    -1.70
    "?
    -1.69
    ·¸
    -1.62
    =%
    -1.60
    :%
    -1.51
    inguished
    -1.50
    POSITIVE LOGITS
    astom
    1.42
    isle
    1.42
    immune
    1.41
    aby
    1.40
    cret
    1.40
    fat
    1.39
     Rapids
    1.36
    chester
    1.34
     Drain
    1.34
    ascus
    1.34
    Activations Density 0.085%

    No Known Activations