© 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. 32045
    Prev
    Next
    INDEX
    Explanations

    references to specific cytokines and their effects in immunology

    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
    419
    +0.17
    0.9%
    320
    +0.15
    0.8%
    271
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.17
    0.02
    419
    +0.15
    0.02
    201
    +0.13
    0.01
    Negative Logits
    etting
    -1.43
    efore
    -1.42
    iNdEx
    -1.41
    ini
    -1.40
    itrile
    -1.34
    cue
    -1.34
    kets
    -1.33
    ductive
    -1.33
    ique
    -1.32
    cludes
    -1.30
    POSITIVE LOGITS
    Ĭ
    2.09
    Ĥ
    2.08
    Ħ
    1.99
    ¦
    1.96
    İ
    1.91
    Īĺ
    1.87
    ķ
    1.87
    ĭ
    1.75
    ¿
    1.69
    Ł
    1.67
    Activations Density 0.083%

    No Known Activations