© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 27837
    Prev
    Next
    INDEX
    Explanations

    terms related to inclusion in various contexts

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.14
    0.8%
    487
    +0.12
    0.7%
    25
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.14
    0.01
    25
    +0.12
    0.01
    347
    +0.10
    0.01
    Negative Logits
    ĨĴ
    -1.94
    »¿
    -1.92
    Į
    -1.88
    ķ
    -1.79
    §
    -1.79
    Ŀ
    -1.78
    unnumbered
    -1.73
    Ļª
    -1.70
    ĵ
    -1.66
    ¸
    -1.65
    POSITIVE LOGITS
    imates
    1.91
    cript
    1.74
    aneous
    1.65
     appears
    1.58
    andidate
    1.53
    paired
    1.52
     limits
    1.52
    andidates
    1.51
    agraph
    1.51
    uer
    1.49
    Activations Density 0.014%

    No Known Activations