Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27499
    Prev
    Next
    INDEX
    Explanations

    parentheses in the text

    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
    221
    +0.12
    0.7%
    310
    +0.11
    0.6%
    72
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.12
    0.24
    486
    +0.11
    0.16
    154
    +0.10
    0.13
    Negative Logits
    es
    -1.56
    eker
    -1.55
    ahl
    -1.54
    mighty
    -1.53
    ema
    -1.49
    eking
    -1.49
    oth
    -1.49
    iere
    -1.46
    heer
    -1.38
    ätt
    -1.36
    POSITIVE LOGITS
     Posts
    1.50
    assadors
    1.34
     Katie
    1.26
     Squadron
    1.24
    rons
    1.23
     Serge
    1.22
    ó
    1.22
     Choice
    1.21
    Posts
    1.21
     deduction
    1.21
    Activations Density 0.436%

    No Known Activations