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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29155
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    427
    +0.17
    1.0%
    54
    +0.13
    0.7%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.17
    0.00
    1
    -0.13
    0.00
    2
    -0.11
    0.00
    Negative Logits
    TypeDef
    -1.75
    ophila
    -1.66
    alg
    -1.63
    StackTrace
    -1.61
    och
    -1.57
    00001
    -1.48
    elen
    -1.47
    Classes
    -1.45
    ETHOD
    -1.45
    oir
    -1.43
    POSITIVE LOGITS
    ħ
    1.79
     directed
    1.73
    Ģ
    1.71
                           
    1.63
    ↵                   
    1.63
    ↵                      
    1.63
                                                            
    1.63
    ↵↵      
    1.63
    <|outofrange|>
    1.63
    ↵                            
    1.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.