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. 27414
    Prev
    Next
    INDEX
    Explanations

    content related to entertainment

    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
    156
    +0.29
    1.7%
    365
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.29
    0.03
    271
    +0.12
    0.01
    203
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.61
    Į
    -2.23
    §
    -2.20
    ĨĴ
    -2.13
    ľĵ
    -2.11
    į
    -2.10
     yours
    -1.97
    apine
    -1.90
    ½
    -1.87
     hers
    -1.87
    POSITIVE LOGITS
    80211
    1.82
    ister
    1.59
    "}](#
    1.50
    istry
    1.49
    Box
    1.47
    ious
    1.42
    isty
    1.39
     Area
    1.38
    ist
    1.38
     area
    1.37
    Activations Density 3.669%

    No Known Activations