© 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. 27813
    Prev
    Next
    INDEX
    Explanations

    references to OpenGL

    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
    55
    +0.10
    0.6%
    255
    +0.10
    0.6%
    36
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.02
    146
    +0.10
    0.02
    394
    +0.10
    0.02
    Negative Logits
    ¿½
    -3.12
    ¿
    -2.72
    Īĺ
    -2.61
    ´
    -2.46
    Ģ
    -2.26
    Ĥ
    -2.22
    »
    -2.18
    ĥ
    -2.18
    ľĵ
    -2.17
    ½
    -2.15
    POSITIVE LOGITS
    ERC
    2.20
    FW
    2.00
    IVE
    1.95
    DO
    1.87
    PCM
    1.84
    ERTY
    1.83
    CPU
    1.83
    IST
    1.83
    ART
    1.82
    CC
    1.81
    Activations Density 0.016%

    No Known Activations