© 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. 24351
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate additional information or elaboration

    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
    330
    +0.12
    0.7%
    184
    +0.11
    0.6%
    399
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.12
    0.05
    330
    +0.11
    0.05
    421
    +0.11
    0.04
    Negative Logits
    aple
    -1.66
    omb
    -1.54
    apest
    -1.54
     lovers
    -1.40
    ogether
    -1.39
    elijk
    -1.38
    esides
    -1.37
    inib
    -1.35
    ovial
    -1.35
    printStackTrace
    -1.35
    POSITIVE LOGITS
    Ĭ
    2.28
    ¼
    2.15
    ij
    2.09
    ±
    2.03
    ¾
    1.66
    ħ
    1.63
    bie
    1.61
    ©
    1.59
    ·¸
    1.57
    Ĥ¬
    1.55
    Activations Density 0.122%

    No Known Activations