© 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. 29019
    Prev
    Next
    INDEX
    Explanations

    expressions of magnitude or definitive characteristics

    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
    458
    +0.14
    0.8%
    356
    +0.12
    0.6%
    437
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.55
    56
    +0.12
    0.18
    203
    +0.11
    0.38
    Negative Logits
    ANCE
    -1.90
     ↵
    -1.65
    istically
    -1.59
     nonetheless
    -1.43
    ENTIAL
    -1.42
     alive
    -1.39
    >{
    -1.34
     members
    -1.31
     subsequ
    -1.29
     pointing
    -1.26
    POSITIVE LOGITS
    ¦
    2.53
    ¾
    2.39
    ®
    2.29
    §
    2.29
    ´
    2.23
    ·
    2.20
    ¥
    2.20
    ²
    2.17
    ĥ½
    2.07
    »
    2.01
    Activations Density 3.574%

    No Known Activations