© 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. 4-RES-SM
    11. 13772
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal feelings 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    416
    +0.13
    0.7%
    301
    +0.12
    0.7%
    461
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.13
    0.08
    163
    +0.12
    0.06
    416
    +0.12
    0.06
    Negative Logits
    Ħ
    -2.94
    »¿
    -2.86
    ľ
    -2.37
    ij
    -2.35
    Ļª
    -2.31
    Īĺ
    -2.23
    º
    -2.17
    ¸
    -2.15
     ↵
    -2.13
    -2.13
    POSITIVE LOGITS
    'm
    2.77
     cannot
    2.60
     am
    2.53
     fail
    2.38
     want
    2.35
     doubt
    2.32
     don
    2.31
     cant
    2.30
     gotta
    2.26
     need
    2.25
    Activations Density 0.195%

    No Known Activations