© 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 EvalsExportsinterp-engineNEWAPI 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. 24336
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or terms related to organizations or companies

    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
    469
    +0.21
    1.1%
    434
    +0.12
    0.7%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.21
    0.08
    329
    +0.12
    0.04
    303
    +0.11
    0.07
    Negative Logits
    Īĺ
    -2.81
    ±
    -2.64
    Į
    -2.62
    ¾
    -2.61
    ¯
    -2.58
    ¼
    -2.55
    ĻĤ
    -2.55
    Ĥ
    -2.51
    ĭ
    -2.49
    Ĥ¬
    -2.39
    POSITIVE LOGITS
    tons
    1.84
    ções
    1.59
    ción
    1.55
    hline
    1.54
    places
    1.54
    """
    1.50
    clip
    1.49
    ção
    1.49
    Hz
    1.44
    pire
    1.43
    Activations Density 1.339%

    No Known Activations