© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27860
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically periods at the end of sentences

    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
    453
    +0.12
    0.7%
    169
    +0.12
    0.7%
    313
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.14
    271
    +0.12
    0.07
    156
    +0.12
    0.07
    Negative Logits
    ¯
    -2.42
    ĨĴ
    -2.27
    Ĥ
    -2.22
    Ģ
    -2.06
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.95
    ↵        ↵
    -1.91
    -1.91
    ↵↵
    -1.91
    ↵
    -1.91
    -1.91
    POSITIVE LOGITS
    irth
    1.77
    esium
    1.71
     brighter
    1.60
     ye
    1.46
     fathers
    1.40
    sson
    1.39
    uda
    1.39
     hab
    1.38
    }$\
    1.37
     Utah
    1.32
    Activations Density 0.083%

    No Known Activations