© 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. 29865
    Prev
    Next
    INDEX
    Explanations

    numeric values and version identifiers

    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
    198
    +0.15
    0.8%
    499
    +0.12
    0.7%
    17
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.15
    0.05
    203
    +0.12
    0.05
    452
    +0.11
    0.04
    Negative Logits
     opposing
    -1.54
     inequ
    -1.42
     defending
    -1.42
    ¯
    -1.36
     collecting
    -1.33
    .^\[[@
    -1.33
     interested
    -1.32
     orderly
    -1.31
     others
    -1.31
    otropic
    -1.29
    POSITIVE LOGITS
    IZE
    1.65
    GHz
    1.52
    %"
    1.51
    cup
    1.51
    WARE
    1.49
     GHz
    1.47
    ITY
    1.47
    createElement
    1.43
    asone
    1.40
    framework
    1.38
    Activations Density 0.152%

    No Known Activations