© 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. 1-RES-SM
    11. 29563
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ak" or related variations that signify specific contexts or entities

    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
    2
    +0.13
    0.7%
    223
    +0.12
    0.7%
    477
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.13
    0.03
    223
    +0.12
    0.02
    347
    +0.11
    0.02
    Negative Logits
    Ķ
    -1.91
    Ĥ
    -1.85
     course
    -1.67
    ¼
    -1.63
    ortion
    -1.56
    ollowing
    -1.45
    ferentially
    -1.45
    ighting
    -1.44
    YING
    -1.42
    Ĺ
    -1.41
    POSITIVE LOGITS
    ings
    2.00
    izumab
    1.97
    shi
    1.90
    arta
    1.85
    arios
    1.81
    asone
    1.80
    shire
    1.76
    rams
    1.76
    ioni
    1.73
    hurst
    1.69
    Activations Density 0.072%

    No Known Activations