© 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. 28641
    Prev
    Next
    INDEX
    Explanations

    sections of text related to software licensing and legal disclaimers

    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
    263
    +0.11
    0.7%
    427
    +0.10
    0.7%
    157
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.11
    0.01
    230
    +0.10
    0.01
    499
    +0.10
    0.01
    Negative Logits
    Ĺ
    -3.64
    Ŀ
    -3.52
    ·¸
    -3.45
    ķ
    -3.43
    ¯
    -3.42
    ĻĤ
    -3.42
    ¨
    -3.39
    ¬
    -3.29
    Ļª
    -3.29
    Ĭ
    -3.26
    POSITIVE LOGITS
    framework
    1.59
     Agreement
    1.57
     waiver
    1.57
    ierno
    1.55
    roup
    1.53
    UMENT
    1.52
    umab
    1.47
     Statement
    1.42
    ár
    1.41
    ISM
    1.40
    Activations Density 0.029%

    No Known Activations