© 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 EvalsExportsAPI 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. 26377
    Prev
    Next
    INDEX
    Explanations

    elements and URLs related to code repositories

    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
    324
    +0.12
    0.7%
    391
    +0.10
    0.6%
    422
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.12
    0.02
    329
    +0.10
    0.03
    470
    +0.10
    0.02
    Negative Logits
    ľ
    -2.23
    Ļª
    -2.17
    ľĵ
    -2.10
    ĻĤ
    -1.96
    Ĥ
    -1.95
    ¿½
    -1.92
    ´
    -1.92
    ħ
    -1.87
    ·¸
    -1.86
    ĭ
    -1.85
    POSITIVE LOGITS
    -*
    1.40
     grave
    1.40
     yourself
    1.37
    ository
    1.35
    añ
    1.33
    Ïģί
    1.33
    ilen
    1.31
    иÑĤ
    1.31
    0020
    1.29
    0028
    1.26
    Activations Density 0.413%

    No Known Activations