© 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. 24510
    Prev
    Next
    INDEX
    Explanations

    terminology and characteristics related to data structures and programming elements

    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
    160
    +0.13
    0.7%
    492
    +0.13
    0.7%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.13
    0.10
    303
    +0.13
    0.09
    160
    +0.12
    0.12
    Negative Logits
    ij
    -2.47
    Ĩ
    -2.45
    Ĵ
    -2.40
    ¿½
    -2.39
    ħ
    -2.35
    Ł
    -2.29
    Ĥ
    -2.29
    ģ
    -2.19
    ¸
    -2.18
    ĥ½
    -2.15
    POSITIVE LOGITS
    )$)
    1.77
    "))
    1.60
    fony
    1.57
    inib
    1.57
     ups
    1.56
    ulp
    1.47
    reat
    1.44
    olve
    1.43
     purposes
    1.43
    istry
    1.43
    Activations Density 2.899%

    No Known Activations