© 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. 2-RES-SM
    11. 11200
    Prev
    Next
    INDEX
    Explanations

    code-related structure and definitions

    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
    261
    +0.12
    0.7%
    235
    +0.12
    0.7%
    221
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.12
    0.11
    0
    +0.12
    0.07
    261
    +0.11
    0.03
    Negative Logits
    kerchief
    -1.70
    etine
    -1.45
    ptin
    -1.44
    lint
    -1.44
    amid
    -1.41
    ubicin
    -1.38
     promised
    -1.31
    ochemical
    -1.31
    numbered
    -1.29
     oath
    -1.25
    POSITIVE LOGITS
     niche
    1.40
     sino
    1.38
    openh
    1.33
    .
    1.28
    »¿
    1.28
    erent
    1.27
     focal
    1.26
    utum
    1.22
     receptive
    1.22
     AFL
    1.22
    Activations Density 4.670%

    No Known Activations