© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax related to function definitions or code structures

    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
    258
    +0.20
    1.2%
    23
    +0.19
    1.1%
    478
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.20
    0.13
    23
    +0.19
    0.11
    217
    +0.15
    0.10
    Negative Logits
    ĻĤ
    -3.12
    ¿½
    -3.10
    »¿
    -2.70
    Ļª
    -2.66
    ´
    -2.56
    ķ
    -2.51
    ¬
    -2.51
    Ĭ
    -2.48
    ²
    -2.46
    ļ
    -2.44
    POSITIVE LOGITS
    json
    2.24
    xml
    2.07
    yaml
    1.99
    googleapis
    1.97
    php
    1.84
    xsd
    1.81
    Common
    1.74
    txt
    1.69
    xsl
    1.56
    tgz
    1.55
    Activations Density 1.040%

    No Known Activations