© 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. 26443
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception or belief

    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
    23
    +0.23
    1.3%
    376
    +0.16
    0.9%
    335
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.23
    0.04
    83
    +0.16
    0.03
    335
    +0.11
    0.03
    Negative Logits
    §
    -3.34
    ¸
    -3.08
    ĭ
    -3.05
    İ
    -3.00
    Ģ
    -2.92
    Ī
    -2.84
    į
    -2.83
    ¤
    -2.73
    ´
    -2.71
    ·¸
    -2.59
    POSITIVE LOGITS
     endless
    1.51
    hal
    1.49
    hope
    1.45
    lest
    1.43
    PECT
    1.42
    hur
    1.39
     hopeless
    1.38
    hing
    1.36
    sterdam
    1.36
    olation
    1.34
    Activations Density 0.128%

    No Known Activations