© 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. 29837
    Prev
    Next
    INDEX
    Explanations

    technical keywords and symbols related to coding instructions and structures

    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
    187
    +0.14
    0.8%
    178
    +0.12
    0.7%
    508
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.14
    0.00
    187
    +0.12
    0.07
    379
    +0.12
    0.15
    Negative Logits
     ">
    -1.57
    amsfonts
    -1.46
    :)
    -1.39
    ttp
    -1.37
    gium
    -1.37
     Collaboration
    -1.36
    amsmath
    -1.28
    ðŁ
    -1.27
     paramet
    -1.26
    amethasone
    -1.26
    POSITIVE LOGITS
    ®
    3.88
    <|outofrange|>
    3.60
    ↵
    3.60
    3.60
    č↵č↵
    3.60
    ↵        ↵
    3.60
    <|outofrange|>
    3.60
    č↵
    3.60
    3.60
    ↵
    3.60
    Activations Density 4.154%

    No Known Activations