© 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. 2-MLP-SM
    6. 25541
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulties in learning and engagement in various activities

    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
    23
    +0.15
    0.9%
    185
    +0.14
    0.8%
    289
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.15
    0.08
    250
    +0.14
    0.05
    289
    +0.11
    0.10
    Negative Logits
    usiness
    -1.72
    etc
    -1.66
    illion
    -1.62
    starter
    -1.58
    illin
    -1.51
    va
    -1.50
     etc
    -1.46
    asek
    -1.46
    uncher
    -1.44
    anno
    -1.39
    POSITIVE LOGITS
     students
    1.60
     inches
    1.49
    '?"
    1.43
     startling
    1.41
     confounding
    1.40
    aturing
    1.39
     proof
    1.37
    :`
    1.34
    fered
    1.34
    ched
    1.32
    Activations Density 3.589%

    No Known Activations