© 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. 26651
    Prev
    Next
    INDEX
    Explanations

    references to "rails" or similar constructs in various contexts

    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
    71
    +0.12
    0.7%
    162
    +0.10
    0.6%
    371
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.12
    0.01
    112
    +0.10
    0.01
    506
    +0.10
    0.01
    Negative Logits
    «
    -1.73
    ¿
    -1.70
    ´
    -1.51
    ©
    -1.47
     Fly
    -1.47
    §
    -1.47
    ¯
    -1.46
    ran
    -1.45
    Ļª
    -1.45
     ransom
    -1.44
    POSITIVE LOGITS
    pieces
    1.95
    notes
    1.91
    erne
    1.86
    pot
    1.83
    "}](#
    1.81
    yard
    1.76
    ios
    1.75
    guns
    1.72
    istry
    1.70
    vue
    1.69
    Activations Density 0.011%

    No Known Activations