© 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. 26683
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistics or metrics

    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
    307
    +0.13
    0.8%
    46
    +0.12
    0.7%
    113
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.04
    307
    +0.12
    0.03
    445
    +0.12
    0.02
    Negative Logits
     difference
    -1.60
    ife
    -1.43
    opic
    -1.41
     superiority
    -1.41
     Guidelines
    -1.38
     theory
    -1.38
     principle
    -1.35
    here
    -1.34
    ologies
    -1.33
    "}](#
    -1.29
    POSITIVE LOGITS
    ¿
    2.31
    ¬
    2.21
    ¿½
    2.12
    ¾
    1.92
    ²
    1.91
    ®
    1.89
    ¶
    1.85
    º
    1.78
    ĻĤ
    1.77
    Ĭ
    1.74
    Activations Density 0.223%

    No Known Activations