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. 27629
    Prev
    Next
    INDEX
    Explanations

    specific financial or economic terms related to monetary values

    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
    286
    +0.15
    0.9%
    410
    +0.13
    0.8%
    125
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.15
    0.01
    468
    +0.13
    0.01
    293
    +0.11
    0.01
    Negative Logits
    abbit
    -1.67
    aling
    -1.56
    aning
    -1.53
    thing
    -1.47
    ights
    -1.42
    phants
    -1.42
    phant
    -1.41
     ?"
    -1.40
     studying
    -1.39
    haps
    -1.39
    POSITIVE LOGITS
    etts
    1.49
    hered
    1.37
    RP
    1.36
    etto
    1.35
    ucc
    1.35
     Buc
    1.32
    RU
    1.28
    seud
    1.27
    ulators
    1.27
    nut
    1.27
    Activations Density 0.009%

    No Known Activations