© 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. 2-RES-SM
    11. 13310
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and self-reference

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    143
    +0.17
    0.9%
    23
    +0.15
    0.8%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.17
    0.08
    143
    +0.15
    0.05
    356
    +0.13
    0.06
    Negative Logits
    Ļª
    -4.37
    ĻĤ
    -4.18
    °
    -4.00
    Īĺ
    -3.90
    Ģ
    -3.79
    ©
    -3.60
    ij
    -3.60
    ļ
    -3.54
    ¼
    -3.51
    ł
    -3.51
    POSITIVE LOGITS
     alike
    1.76
     dove
    1.59
    ched
    1.56
     wound
    1.56
     double
    1.52
     realized
    1.50
    ching
    1.50
    aned
    1.47
     figured
    1.44
     bree
    1.44
    Activations Density 0.570%

    No Known Activations