© 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. 29568
    Prev
    Next
    INDEX
    Explanations

    instances of naming or nomenclature-related terms

    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
    470
    +0.15
    0.9%
    376
    +0.13
    0.7%
    33
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.15
    0.04
    56
    +0.13
    0.01
    203
    +0.12
    0.03
    Negative Logits
    unks
    -1.96
    agers
    -1.94
    lying
    -1.60
    ills
    -1.60
    iol
    -1.57
    uff
    -1.56
    '));
    -1.56
    king
    -1.54
    ian
    -1.53
    iam
    -1.52
    POSITIVE LOGITS
     styles
    1.89
     issue
    1.71
     style
    1.62
     devices
    1.61
     disorders
    1.55
     hazard
    1.55
     disorder
    1.53
    Ĥ¬
    1.50
    roup
    1.50
     Instruments
    1.49
    Activations Density 3.596%

    No Known Activations