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. Residuals
    5. 1-RES-SM
    6. 26781
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in text formatting

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    382
    +0.12
    0.7%
    416
    +0.11
    0.6%
    214
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.01
    315
    +0.11
    0.02
    337
    +0.10
    0.02
    Negative Logits
     impression
    -1.40
    opter
    -1.36
     mood
    -1.33
     grasp
    -1.33
    caster
    -1.33
     sense
    -1.31
    bigr
    -1.29
    "—
    -1.29
    casters
    -1.27
     turnout
    -1.27
    POSITIVE LOGITS
    ¿½
    3.14
    ¥
    3.08
    §
    3.06
    ½
    3.05
                                                          
    2.96
    ↵          
    2.96
                                                                  
    2.96
    ↵↵    
    2.96
     ↵   
    2.96
    <|outofrange|>
    2.96
    Activations Density 0.090%

    No Known Activations