© 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. 24718
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic creativity and expression

    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
    407
    +0.14
    0.8%
    210
    +0.12
    0.7%
    330
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.14
    0.08
    130
    +0.12
    0.14
    165
    +0.12
    0.11
    Negative Logits
    ´
    -2.17
    ³
    -2.02
    ¿
    -1.84
    ij
    -1.69
    »
    -1.64
    ©
    -1.63
     light
    -1.55
    ĺ
    -1.50
    ķ
    -1.46
    £
    -1.44
    POSITIVE LOGITS
    zilla
    1.92
    ulus
    1.72
    inux
    1.72
    renthood
    1.68
    wered
    1.62
    ppa
    1.52
    rella
    1.51
    cember
    1.46
     aside
    1.44
    izabeth
    1.41
    Activations Density 2.419%

    No Known Activations