© 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. 27430
    Prev
    Next
    INDEX
    Explanations

    constructs and declarations related to programming and 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/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
    365
    +0.13
    0.7%
    418
    +0.13
    0.7%
    309
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.13
    0.04
    303
    +0.13
    0.03
    189
    +0.13
    0.02
    Negative Logits
    ľĵ
    -2.06
     indic
    -1.60
    Ĩ
    -1.59
    ħ
    -1.58
    ricanes
    -1.57
    ¹
    -1.56
     wheels
    -1.54
     peaks
    -1.47
    cels
    -1.41
     ions
    -1.41
    POSITIVE LOGITS
    ctrine
    1.55
     Chapter
    1.47
    omenclature
    1.43
     ours
    1.39
    liography
    1.36
     theirs
    1.34
    rapper
    1.34
    rench
    1.31
    sted
    1.31
     yours
    1.30
    Activations Density 0.348%

    No Known Activations