© 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. 2-MLP-SM
    11. 25646
    Prev
    Next
    INDEX
    Explanations

    terms related to linear algebra and mathematical concepts involving linearity

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    308
    +0.14
    0.8%
    38
    +0.12
    0.7%
    374
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.14
    0.01
    23
    +0.12
    0.01
    377
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -3.13
    »¿
    -3.07
    İ
    -3.02
    Īĺ
    -3.00
    ĥ½
    -2.96
    ĭ
    -2.95
    ®
    -2.87
    ľĵ
    -2.83
    ļ
    -2.82
    ·¸
    -2.69
    POSITIVE LOGITS
     "</
    1.74
    ITED
    1.59
     color
    1.58
    lemental
    1.44
    ção
    1.44
     alkal
    1.37
     pur
    1.37
     dark
    1.36
     subjective
    1.35
     colors
    1.34
    Activations Density 0.220%

    No Known Activations