© 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 EvalsExportsAPI 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. 29206
    Prev
    Next
    INDEX
    Explanations

    references to stages or phases in processes or narratives

    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
    +0.20
    1.2%
    376
    +0.18
    1.0%
    209
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.20
    0.01
    240
    +0.18
    0.01
    168
    +0.12
    0.01
    Negative Logits
    ©
    -3.01
    ½
    -2.85
    ĵ
    -2.82
    Ń
    -2.80
    ±
    -2.80
    Ŀ
    -2.78
    Ĵ
    -2.69
    §
    -2.68
    İ
    -2.68
    ķ
    -2.67
    POSITIVE LOGITS
    heet
    2.22
    hell
    2.12
    arily
    2.03
    elle
    2.02
    creen
    1.95
    heets
    1.91
    burg
    1.83
    oon
    1.71
    aho
    1.70
    arity
    1.63
    Activations Density 0.036%

    No Known Activations