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. 27255
    Prev
    Next
    INDEX
    Explanations

    references to common stock in financial contexts

    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
    +0.16
    0.9%
    285
    +0.14
    0.8%
    433
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.16
    0.01
    240
    +0.14
    0.01
    448
    +0.11
    0.01
    Negative Logits
    AMA
    -1.36
    aped
    -1.34
    eva
    -1.33
    acking
    -1.30
    actual
    -1.28
     thee
    -1.24
    acked
    -1.24
    née
    -1.24
    ooth
    -1.23
    oard
    -1.21
    POSITIVE LOGITS
     denomin
    1.69
    het
    1.66
     denominator
    1.52
    ulence
    1.44
    tons
    1.42
    fonts
    1.42
    wealth
    1.40
    ainties
    1.39
    eous
    1.38
    places
    1.38
    Activations Density 0.597%

    No Known Activations