© 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. 30367
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Hills."

    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
    156
    +0.18
    1.1%
    260
    +0.14
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.18
    0.01
    259
    +0.14
    0.01
    31
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.37
    ¯
    -2.16
    ¦
    -2.13
    §
    -2.10
    ĺ
    -2.07
    ı
    -1.97
    Ĵ
    -1.95
    °
    -1.93
    Ŀ
    -1.88
    ľĵ
    -1.82
    POSITIVE LOGITS
    bank
    2.25
    dale
    2.24
    ong
    2.01
    burg
    2.00
    chitz
    1.89
    hurst
    1.89
    opan
    1.89
    Bank
    1.86
    bourne
    1.85
    iale
    1.80
    Activations Density 0.014%

    No Known Activations