© 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. 25942
    Prev
    Next
    INDEX
    Explanations

    repeated references to the state of Maryland

    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
    +0.17
    1.0%
    508
    +0.13
    0.8%
    182
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.17
    0.01
    105
    +0.13
    0.01
    182
    +0.13
    0.01
    Negative Logits
     slavery
    -1.78
     terrible
    -1.71
     horrible
    -1.68
     Negro
    -1.66
     blacks
    -1.65
     African
    -1.64
     things
    -1.56
     persecution
    -1.53
     great
    -1.52
     complete
    -1.51
    POSITIVE LOGITS
    ĥ½
    2.56
    ¥
    2.48
    §
    2.47
    º
    2.45
    Į
    2.44
    ģ
    2.40
    Ĵ
    2.26
    »
    2.26
    ·
    2.25
    «
    2.24
    Activations Density 0.006%

    No Known Activations