© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 10763
    Prev
    Next
    INDEX
    Explanations

    registration or identification codes, measurement values, and numerical data

    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
    98
    +0.18
    1.0%
    507
    +0.17
    1.0%
    316
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.18
    0.07
    2
    +0.17
    0.13
    317
    +0.13
    0.13
    Negative Logits
    Īĺ
    -3.84
    ľĵ
    -3.84
    »¿
    -3.71
    ĻĤ
    -3.56
    £
    -3.48
    ĥ
    -3.47
    ģ
    -3.32
    Ŀ
    -3.29
    ¿
    -3.19
    Ļª
    -3.14
    POSITIVE LOGITS
    inho
    1.57
    ème
    1.55
    ostream
    1.52
    oler
    1.49
    prote
    1.45
    ocard
    1.42
    sworth
    1.41
    overnment
    1.40
    tera
    1.37
    olin
    1.37
    Activations Density 7.620%

    No Known Activations