© 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. 28212
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience or 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/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
    369
    +0.17
    1.0%
    478
    +0.15
    0.9%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.17
    0.10
    299
    +0.15
    0.08
    356
    +0.12
    0.08
    Negative Logits
    limiting
    -1.76
    °
    -1.75
    ably
    -1.69
    ŀ
    -1.68
    misc
    -1.67
    14514500
    -1.58
    imeters
    -1.55
    Ħ
    -1.52
    emas
    -1.49
    imeter
    -1.48
    POSITIVE LOGITS
    brahim
    2.09
    bn
    1.93
     hope
    1.89
     trust
    1.84
     dream
    1.79
     promise
    1.78
    reland
    1.77
     envy
    1.77
     dread
    1.69
    ÃŃm
    1.68
    Activations Density 0.538%

    No Known Activations