© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28216
    Prev
    Next
    INDEX
    Explanations

    the word "circum," likely related to circumstantial or circumflex terms

    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
    111
    +0.17
    1.0%
    510
    +0.12
    0.7%
    376
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.01
    510
    +0.12
    0.01
    240
    +0.12
    0.01
    Negative Logits
    Ķ
    -2.86
    ĨĴ
    -2.65
    ĥ
    -2.51
    ¯
    -2.42
    »¿
    -2.30
    Ļª
    -2.29
    ¶
    -2.10
    ļ
    -2.06
    ¦
    -2.05
    ¢
    -2.04
    POSITIVE LOGITS
     slot
    1.84
    :`
    1.70
     slots
    1.60
     hairs
    1.55
    thon
    1.55
    scribed
    1.54
    stery
    1.44
    stalk
    1.42
    stance
    1.41
    scription
    1.37
    Activations Density 0.010%

    No Known Activations