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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26381
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to community and collaborative 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
    +0.20
    1.1%
    458
    +0.10
    0.6%
    181
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.20
    0.10
    23
    +0.10
    0.06
    181
    +0.10
    0.10
    Negative Logits
     seats
    -1.82
    orbent
    -1.82
    .“
    -1.74
    arias
    -1.73
    lessly
    -1.72
    starter
    -1.68
    (@
    -1.68
    upon
    -1.67
    thems
    -1.63
    lections
    -1.63
    POSITIVE LOGITS
    ritical
    1.49
     whom
    1.46
    odal
    1.41
     Navy
    1.36
    inned
    1.36
     Bridge
    1.33
    umann
    1.33
    bringing
    1.27
     psychologist
    1.26
    roke
    1.25
    Activations Density 1.312%

    No Known Activations