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. 27312
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or terms that emphasize recurrence

    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
    129
    +0.12
    0.7%
    313
    +0.11
    0.6%
    163
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.12
    0.09
    87
    +0.11
    0.08
    249
    +0.11
    0.07
    Negative Logits
    ı
    -2.06
    Ĭ
    -2.04
    ķ
    -2.02
    Ĵ
    -2.01
    ¸
    -1.93
    Ļ
    -1.86
    ·
    -1.84
    Ļª
    -1.80
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.78
    ¯
    -1.76
    POSITIVE LOGITS
    version
    1.60
    blogspot
    1.58
     themselves
    1.57
     NOTICE
    1.48
    fire
    1.48
    adoc
    1.46
    keeper
    1.46
    ness
    1.44
    wise
    1.43
    ical
    1.40
    Activations Density 0.159%

    No Known Activations