© 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. 25241
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling and character description

    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
    239
    +0.14
    0.8%
    135
    +0.13
    0.7%
    497
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.14
    0.06
    108
    +0.13
    0.09
    497
    +0.12
    -0.03
    Negative Logits
    ¿½
    -3.02
    Į
    -2.95
    ij
    -2.70
    ķ
    -2.67
    °
    -2.61
    ¿
    -2.52
    Ĥ¬
    -2.52
    ´
    -2.51
    ¦
    -2.48
    Ļª
    -2.36
    POSITIVE LOGITS
     itself
    1.69
     polls
    1.62
    license
    1.52
     yourselves
    1.52
    orb
    1.49
     themselves
    1.48
    ibles
    1.48
    icles
    1.47
    urrection
    1.44
    azine
    1.43
    Activations Density 2.396%

    No Known Activations