© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11932
    Prev
    Next
    INDEX
    Explanations

    code-related assertions and logical conditions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.30
    2.3%
    21
    +0.16
    1.2%
    280
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.30
    0.06
    397
    +0.16
    0.21
    9
    +0.09
    0.17
    Negative Logits
     Assembly
    -1.23
    rangian
    -1.20
     assembly
    -1.19
     term
    -1.15
     Infrastructure
    -1.13
    ctors
    -1.13
     organ
    -1.11
     library
    -1.09
     Overview
    -1.09
    sembly
    -1.07
    POSITIVE LOGITS
    Ī
    2.20
    Į
    2.12
    IJ
    2.10
    ľĵ
    2.08
    ł
    2.03
    ©
    1.99
    Ĩ
    1.97
    ī
    1.96
    İ
    1.94
    ĺ
    1.92
    Activations Density 4.018%

    No Known Activations