© 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. 2-RES-SM
    11. 10023
    Prev
    Next
    INDEX
    Explanations

    references to various types of wires and wiring in 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
    156
    +0.16
    0.9%
    256
    +0.14
    0.8%
    306
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.16
    0.01
    376
    +0.14
    0.00
    80
    +0.12
    0.02
    Negative Logits
    quer
    -1.81
     resignation
    -1.71
     certain
    -1.63
     departure
    -1.54
     surprise
    -1.51
    thood
    -1.50
     practice
    -1.50
     desire
    -1.47
     bargaining
    -1.45
     rebut
    -1.45
    POSITIVE LOGITS
    tap
    2.19
    Ĺ
    2.10
    ups
    2.08
    ¢
    2.08
    ¹
    2.04
    ®
    2.00
    neck
    1.96
    ģ
    1.95
    Ķ
    1.93
    Ģ
    1.92
    Activations Density 0.278%

    No Known Activations