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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28743
    Prev
    Next
    INDEX
    Explanations

    documentation or comments in code snippets

    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
    410
    +0.15
    0.9%
    118
    +0.14
    0.8%
    11
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.03
    165
    +0.14
    0.02
    416
    +0.13
    0.02
    Negative Logits
     merits
    -1.62
     1998
    -1.56
     2006
    -1.56
     2008
    -1.55
     2004
    -1.55
     PBS
    -1.52
     2002
    -1.52
     2007
    -1.52
     2009
    -1.49
     Fox
    -1.47
    POSITIVE LOGITS
    ½
    2.71
    ¿½
    2.24
    ³
    2.03
    ĻĤ
    1.98
    ↵
    1.97
    1.97
    ↵↵
    1.97
    č↵č↵
    1.97
    ↵↵↵
    1.97
    ↵
    1.97
    Activations Density 0.249%

    No Known Activations