© 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. 26541
    Prev
    Next
    INDEX
    Explanations

    references to selective criteria and processes in medical and technical contexts

    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
    172
    +0.14
    0.8%
    391
    +0.14
    0.8%
    59
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.14
    0.05
    59
    +0.14
    0.04
    74
    +0.13
    0.04
    Negative Logits
     guess
    -1.66
     lately
    -1.49
    SUCCESS
    -1.45
     spoken
    -1.43
     dreamed
    -1.42
     gotten
    -1.42
     taken
    -1.40
     expecting
    -1.40
     time
    -1.36
     wait
    -1.36
    POSITIVE LOGITS
    µ
    3.67
    Ĭ
    3.66
    Ĥ
    3.59
    Ĥ¬
    3.44
    ĻĤ
    3.42
    ĸ´
    3.41
    ·¸
    3.37
    ħ
    3.36
    ¿
    3.29
    ±
    3.28
    Activations Density 0.518%

    No Known Activations