© 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. 28858
    Prev
    Next
    INDEX
    Explanations

    URLs or web links in the text

    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
    284
    +0.11
    0.6%
    358
    +0.11
    0.6%
    455
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.11
    0.02
    336
    +0.11
    0.02
    284
    +0.10
    0.02
    Negative Logits
    ellow
    -1.52
    rait
    -1.42
    }</
    -1.41
    noreply
    -1.37
    ired
    -1.36
    iÄĩ
    -1.30
     cross
    -1.30
    esque
    -1.29
    mes
    -1.25
    ousse
    -1.24
    POSITIVE LOGITS
    doibase
    1.46
    license
    1.41
     discretion
    1.33
     lic
    1.32
     yourselves
    1.32
    pntd
    1.31
    rieved
    1.31
     CLAIM
    1.30
    ://
    1.28
    forge
    1.27
    Activations Density 0.038%

    No Known Activations