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. 27314
    Prev
    Next
    INDEX
    Explanations

    latitude references in a geographical 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
    320
    +0.14
    0.8%
    410
    +0.12
    0.7%
    111
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.14
    0.02
    438
    +0.12
    0.02
    53
    +0.12
    0.02
    Negative Logits
    ĸ´
    -3.45
    ¹
    -3.43
    ↵                                            
    -3.39
                
    -3.39
    ↵                                                 
    -3.39
    <|outofrange|>
    -3.39
                                    
    -3.39
    <|outofrange|>
    -3.39
    <|outofrange|>
    -3.39
            ↵ 
    -3.39
    POSITIVE LOGITS
    estone
    2.07
    ibase
    1.92
    estones
    1.79
    itudinal
    1.76
    enos
    1.75
    shots
    1.72
    stown
    1.62
    istics
    1.61
    imes
    1.60
    DH
    1.57
    Activations Density 4.651%

    No Known Activations