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. 27303
    Prev
    Next
    INDEX
    Explanations

    instances of the word "This."

    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
    23
    +0.24
    1.4%
    478
    +0.17
    1.0%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.24
    0.08
    339
    +0.17
    0.06
    401
    +0.14
    0.06
    Negative Logits
    sci
    -1.70
    space
    -1.55
    aware
    -1.49
    ahead
    -1.48
    aho
    -1.43
    ificial
    -1.42
    spaces
    -1.42
    casters
    -1.40
    onaut
    -1.39
    enos
    -1.39
    POSITIVE LOGITS
     happen
    1.91
     same
    1.85
     soit
    1.78
     intercourse
    1.72
     talk
    1.64
     happ
    1.62
     kind
    1.58
     happened
    1.55
     hurt
    1.54
    uesday
    1.53
    Activations Density 4.611%

    No Known Activations