© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28047
    Prev
    Next
    INDEX
    Explanations

    references to the name "Graves" 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
    259
    +0.13
    0.7%
    376
    +0.13
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.13
    0.01
    511
    +0.13
    0.01
    466
    +0.12
    0.01
    Negative Logits
     où
    -1.68
    ching
    -1.52
    pher
    -1.50
     certain
    -1.49
    esides
    -1.46
    aring
    -1.44
     versa
    -1.43
     lasting
    -1.42
     qui
    -1.42
     faire
    -1.40
    POSITIVE LOGITS
    ¹
    2.15
    £
    2.01
    µ
    1.96
    etable
    1.91
    ·¸
    1.86
    erve
    1.77
    hill
    1.77
    ¶
    1.75
    kill
    1.71
    cript
    1.69
    Activations Density 0.018%

    No Known Activations