© 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. 10351
    Prev
    Next
    INDEX
    Explanations

    mentions of copyright and other legal disclaimers related to media

    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
    +0.15
    0.9%
    153
    +0.14
    0.8%
    436
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.15
    0.08
    436
    +0.14
    0.08
    497
    +0.14
    0.03
    Negative Logits
    ctrine
    -1.59
    alent
    -1.56
     nomin
    -1.45
     consortium
    -1.36
     hell
    -1.35
     ([@
    -1.35
    arynge
    -1.34
    ^âĪĴ
    -1.32
    quart
    -1.31
    ainties
    -1.30
    POSITIVE LOGITS
    ĻĤ
    2.61
    ³
    2.38
    Ļ
    2.37
    Ĭ
    2.36
    »
    2.24
    ľ
    2.09
    ²
    2.08
    ľĵ
    2.07
    ©
    2.06
    ±
    2.04
    Activations Density 5.737%

    No Known Activations