© 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. 25483
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions

    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
    92
    +0.15
    0.8%
    478
    +0.13
    0.7%
    145
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.15
    0.05
    145
    +0.13
    0.04
    82
    +0.11
    0.04
    Negative Logits
    Ŀ
    -2.66
    ļ
    -2.61
    Ĺ
    -2.52
    ķ
    -2.45
    ľ
    -2.35
    ĻĤ
    -2.35
    Ľ
    -2.30
    ģ
    -2.28
    ·¸
    -2.28
    ĭ
    -2.22
    POSITIVE LOGITS
    tingham
    2.32
     anymore
    1.92
    oriously
    1.91
    withstanding
    1.81
    yet
    1.54
     yet
    1.54
     hesitate
    1.53
    hin
    1.53
     conclusions
    1.51
    alone
    1.50
    Activations Density 0.173%

    No Known Activations