© 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. 30520
    Prev
    Next
    INDEX
    Explanations

    discussions around media hype

    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
    +0.12
    0.7%
    178
    +0.10
    0.6%
    109
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.01
    47
    +0.10
    0.01
    77
    +0.10
    0.01
    Negative Logits
    unnumbered
    -2.05
    ^](#
    -1.95
    Docket
    -1.66
    hood
    -1.66
    TRODUCTION
    -1.63
    sible
    -1.60
    TY
    -1.56
    ATIONS
    -1.55
     entirety
    -1.51
     ];
    -1.49
    POSITIVE LOGITS
    ģ
    2.18
    «
    2.07
    ī
    2.06
    ®
    2.01
    ļ
    1.99
    caster
    1.99
    £
    1.98
    ĸ
    1.88
    °
    1.87
    ±
    1.86
    Activations Density 0.448%

    No Known Activations