© 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. 28337
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to individuals, particularly in relation to personal experiences or narratives

    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
    98
    +0.15
    0.9%
    436
    +0.13
    0.7%
    10
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.15
    0.08
    10
    +0.13
    0.05
    51
    +0.11
    0.05
    Negative Logits
    stood
    -1.75
     priority
    -1.60
    hold
    -1.53
     respect
    -1.51
     limit
    -1.49
    ring
    -1.47
     focus
    -1.45
    omitempty
    -1.44
    coordinate
    -1.40
     reference
    -1.40
    POSITIVE LOGITS
    IJ
    2.73
    »¿
    2.70
    ĨĴ
    2.38
    ij
    2.32
    ĻĤ
    2.31
    ¿½
    2.14
    Ģ
    2.11
    Ļª
    2.10
    Ĭ
    1.98
    ¸
    1.97
    Activations Density 0.849%

    No Known Activations