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. 12023
    Prev
    Next
    INDEX
    Explanations

    references to significant historical dates and events

    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
    286
    +0.15
    0.8%
    436
    +0.14
    0.8%
    422
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.15
    0.03
    110
    +0.14
    0.02
    51
    +0.12
    0.03
    Negative Logits
    Ļ
    -2.96
    ľĵ
    -2.89
    Ħ
    -2.81
                       
    -2.79
        ↵ 
    -2.79
    <|outofrange|>
    -2.79
    ↵               
    -2.79
    ↵                                                
    -2.79
                            
    -2.79
                               
    -2.79
    POSITIVE LOGITS
    Decided
    1.74
    oslov
    1.72
     anniversary
    1.70
     onward
    1.67
    geois
    1.66
    zent
    1.66
    century
    1.65
     год
    1.64
    stä
    1.63
     onwards
    1.61
    Activations Density 0.078%

    No Known Activations