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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28233
    Prev
    Next
    INDEX
    Explanations

    the presence of various forms of verbs, particularly those related to actions or states of being

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    56
    +0.14
    0.8%
    398
    +0.13
    0.7%
    46
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.14
    0.09
    58
    +0.13
    0.08
    62
    +0.11
    0.06
    Negative Logits
    ī
    -3.67
    Ħ
    -3.57
    Ļ
    -3.46
    Ī
    -3.44
    Ŀ
    -3.42
    ·¸
    -3.40
    Ĵ
    -3.33
    ĭ
    -3.24
    §
    -3.23
    ĵ
    -3.21
    POSITIVE LOGITS
    erville
    1.87
    neck
    1.66
    hill
    1.61
    ently
    1.61
    ashes
    1.58
    ermine
    1.51
    arding
    1.51
    entary
    1.48
    dorff
    1.47
    %--
    1.47
    Activations Density 1.044%

    No Known Activations