© 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. 29358
    Prev
    Next
    INDEX
    Explanations

    references to multiplex and duplex configurations

    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
    196
    +0.15
    0.9%
    156
    +0.15
    0.9%
    338
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.15
    0.01
    40
    +0.15
    0.01
    382
    +0.12
    0.01
    Negative Logits
    orems
    -1.64
     prey
    -1.59
    rely
    -1.55
     faint
    -1.53
    ros
    -1.41
     drag
    -1.40
    ____________
    -1.40
     gradual
    -1.40
    rian
    -1.40
     abuse
    -1.39
    POSITIVE LOGITS
    ®
    2.97
    ¬
    2.74
    ª
    2.43
    ¢
    2.39
    ķ
    2.31
    ¥
    2.28
    ¡
    2.23
    ¶
    2.22
    «
    2.21
    Ĭ
    2.19
    Activations Density 0.008%

    No Known Activations