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. 27374
    Prev
    Next
    INDEX
    Explanations

    the keyword "View" within a programming context

    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
    44
    +0.14
    0.8%
    100
    +0.12
    0.7%
    52
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.14
    0.03
    52
    +0.12
    0.02
    190
    +0.12
    0.02
    Negative Logits
    '?"
    -2.00
    "?"
    -1.95
    ?"
    -1.87
     suppose
    -1.76
     yours
    -1.75
    ]>
    -1.70
     there
    -1.65
    ?'
    -1.65
     venom
    -1.61
     jeopardy
    -1.60
    POSITIVE LOGITS
    ista
    1.87
    ERC
    1.84
    ister
    1.78
    ós
    1.78
    port
    1.75
    aggio
    1.72
    EXPORT
    1.68
    istas
    1.63
    ariant
    1.61
    iew
    1.61
    Activations Density 0.026%

    No Known Activations