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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 12158
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and specifications of products, particularly focusing on measurements and materials

    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
    419
    +0.18
    1.1%
    326
    +0.14
    0.8%
    72
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.27
    156
    +0.14
    0.27
    71
    +0.14
    0.27
    Negative Logits
    »¿
    -2.96
    £
    -2.84
                                     
    -2.83
       ↵ 
    -2.83
    ↵                                
    -2.83
              ↵ 
    -2.83
    č↵                       
    -2.83
    ↵                                       
    -2.83
               
    -2.83
    ↵                                  
    -2.83
    POSITIVE LOGITS
     autism
    1.53
     PTSD
    1.52
    osus
    1.52
    ftware
    1.51
    manif
    1.48
     minors
    1.44
    elen
    1.43
    visiae
    1.36
    vet
    1.35
     families
    1.34
    Activations Density 4.470%

    No Known Activations