© 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. 27018
    Prev
    Next
    INDEX
    Explanations

    references to a specific location named Bethel

    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
    376
    +0.13
    0.7%
    40
    +0.13
    0.7%
    164
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.13
    0.04
    23
    +0.13
    0.04
    494
    +0.12
    0.03
    Negative Logits
    ij
    -3.14
    Ŀ
    -3.09
    ľ
    -2.95
    ĵ
    -2.75
    ³
    -2.66
    Ł
    -2.60
    ½
    -2.56
    ¸
    -2.49
    ´
    -2.48
    Ń
    -2.42
    POSITIVE LOGITS
    antine
    1.99
    igent
    1.73
    aine
    1.73
    uelle
    1.70
    uel
    1.68
    rays
    1.65
    uality
    1.59
    ivals
    1.59
    anguage
    1.58
    lems
    1.58
    Activations Density 6.227%

    No Known Activations