© 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. 12220
    Prev
    Next
    INDEX
    Explanations

    terms related to functions and introductions in programming and documentation

    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
    156
    +0.29
    1.7%
    351
    +0.13
    0.7%
    9
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.29
    0.09
    9
    +0.13
    0.05
    232
    +0.12
    0.06
    Negative Logits
    sburg
    -1.48
    ted
    -1.41
    UAL
    -1.40
    forge
    -1.36
    imus
    -1.34
    IAN
    -1.34
    missions
    -1.28
    ---|---
    -1.28
    my
    -1.28
    MIT
    -1.26
    POSITIVE LOGITS
    cer
    2.00
    rers
    1.82
    xture
    1.80
    ces
    1.79
    ments
    1.78
    rees
    1.76
    isance
    1.76
    ality
    1.75
    velopment
    1.73
    rer
    1.72
    Activations Density 1.603%

    No Known Activations