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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27690
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "lu."

    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
    162
    +0.14
    0.8%
    434
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.02
    56
    +0.13
    0.01
    203
    +0.12
    0.01
    Negative Logits
    hift
    -1.72
     true
    -1.58
    hin
    -1.54
     smooth
    -1.47
     noisy
    -1.45
    '?"
    -1.45
     surjective
    -1.44
     descend
    -1.43
     complain
    -1.40
    taient
    -1.39
    POSITIVE LOGITS
    ĻĤ
    2.40
    ©
    2.25
    ī
    2.24
    ª
    2.09
    ²
    2.01
    Ľ
    1.95
    bourne
    1.90
    ®
    1.84
    ford
    1.76
    ¯
    1.75
    Activations Density 3.608%

    No Known Activations