© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding activities

    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
    309
    +0.14
    0.8%
    305
    +0.14
    0.8%
    53
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.14
    0.02
    37
    +0.14
    0.01
    53
    +0.14
    0.03
    Negative Logits
    ]{}]{}
    -1.61
    ](
    -1.52
    angel
    -1.45
    \].
    -1.45
    åĥı
    -1.43
     inhab
    -1.43
     ](
    -1.43
     exploits
    -1.39
    gos
    -1.38
    ){#
    -1.37
    POSITIVE LOGITS
     Split
    1.68
    Īĺ
    1.62
     Athletics
    1.56
     opener
    1.55
     Strike
    1.53
     Range
    1.52
    oxacin
    1.49
     Create
    1.47
     cmd
    1.47
     False
    1.43
    Activations Density 0.212%

    No Known Activations