Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28907
    Prev
    Next
    INDEX
    Explanations

    references to different species and their classifications in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    +0.17
    1.0%
    283
    +0.14
    0.8%
    301
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.17
    0.02
    321
    +0.14
    0.01
    301
    +0.12
    0.01
    Negative Logits
    ŀ
    -3.45
    º
    -3.44
    ĥ½
    -3.38
    č↵           
    -3.23
    č↵  
    -3.23
               
    -3.23
    ↵        ↵       
    -3.23
    ↵↵            
    -3.23
    <|outofrange|>
    -3.23
     ↵           
    -3.23
    POSITIVE LOGITS
    finder
    1.88
    optera
    1.88
     richness
    1.80
    iverse
    1.70
    liest
    1.69
    lia
    1.66
     remains
    1.65
    ional
    1.62
    lion
    1.57
     varies
    1.56
    Activations Density 0.101%

    No Known Activations