© 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. 2-MLP-SM
    11. 25143
    Prev
    Next
    INDEX
    Explanations

    properties and methods related to get and set operations in programming

    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
    66
    +0.16
    0.9%
    414
    +0.12
    0.7%
    6
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.16
    0.01
    313
    +0.12
    0.02
    97
    +0.12
    0.02
    Negative Logits
     suit
    -1.51
     treating
    -1.47
     organ
    -1.44
     motel
    -1.42
     fund
    -1.41
    lette
    -1.41
    lish
    -1.39
     full
    -1.38
     resc
    -1.33
     stret
    -1.32
    POSITIVE LOGITS
    anges
    1.86
    ember
    1.85
    fileID
    1.60
    iors
    1.51
    schemas
    1.49
    sense
    1.47
    Ĭ
    1.47
    versions
    1.44
    important
    1.43
    cibility
    1.40
    Activations Density 0.205%

    No Known Activations