© 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. 25695
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistical outcomes

    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
    170
    +0.13
    0.7%
    388
    +0.11
    0.6%
    201
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.13
    0.03
    115
    +0.11
    0.05
    388
    +0.11
    0.03
    Negative Logits
    ÃŃf
    -1.71
    sov
    -1.63
    ukin
    -1.56
    ifying
    -1.46
    ifiable
    -1.41
    ocur
    -1.41
    ification
    -1.40
    cul
    -1.38
    unction
    -1.37
     confirm
    -1.36
    POSITIVE LOGITS
     Himself
    1.54
    ĻĤ
    1.51
     row
    1.50
    bones
    1.48
    bone
    1.47
    Ļª
    1.45
    onds
    1.45
    stairs
    1.44
    joy
    1.44
    atha
    1.43
    Activations Density 0.119%

    No Known Activations