© 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. 28698
    Prev
    Next
    INDEX
    Explanations

    technical or programming terms related to configuration and property management in code

    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
    100
    +0.13
    0.7%
    410
    +0.12
    0.7%
    35
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.13
    0.07
    165
    +0.12
    0.08
    374
    +0.10
    0.10
    Negative Logits
    Ĺ
    -3.96
    ĸ
    -3.65
    ħ
    -3.64
    ķ
    -3.56
    Ń
    -3.56
    ļ
    -3.55
    ł
    -3.52
    ©
    -3.51
    »
    -3.50
    ĻĤ
    -3.48
    POSITIVE LOGITS
    ipart
    1.58
     relation
    1.55
    selves
    1.49
     figure
    1.48
     unconscious
    1.40
    inates
    1.39
    ––––––––
    1.37
     constant
    1.35
     equation
    1.34
     studio
    1.33
    Activations Density 0.662%

    No Known Activations