© 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. 28447
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of "too much to do" or overall high expectations

    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
    23
    +0.12
    0.7%
    170
    +0.11
    0.6%
    422
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.07
    56
    +0.11
    -0.03
    433
    +0.11
    0.04
    Negative Logits
    ĭ
    -2.15
    Ī
    -2.12
    Ŀ
    -2.04
    ¾
    -1.97
    ¸
    -1.96
    ł
    -1.87
    Ĩ
    -1.85
    Ħ
    -1.82
    ³
    -1.81
    ¶
    -1.79
    POSITIVE LOGITS
    ength
    1.52
     awe
    1.51
    uminous
    1.51
     distance
    1.46
     ]{}
    1.42
     machine
    1.41
     []
    1.39
     curtain
    1.39
     APPEALS
    1.38
     accl
    1.36
    Activations Density 1.787%

    No Known Activations