© 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. 4-RES-SM
    11. 9269
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and web development

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.24
    1.4%
    268
    +0.15
    0.9%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.24
    0.06
    268
    +0.15
    0.08
    511
    +0.12
    0.07
    Negative Logits
    ©
    -6.14
    Ĭ
    -5.97
    Ħ
    -5.95
    ¼
    -5.92
    ·
    -5.85
    Į
    -5.83
    ł
    -5.82
    §
    -5.82
    ĵ
    -5.81
    ĥ
    -5.81
    POSITIVE LOGITS
    ource
    3.63
    cript
    3.57
    pace
    3.53
    ystems
    3.44
    heet
    3.30
    paces
    3.29
    erver
    3.28
    creen
    2.90
    heets
    2.82
    plit
    2.79
    Activations Density 0.553%

    No Known Activations