© 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. 1-RES-SM
    11. 27437
    Prev
    Next
    INDEX
    Explanations

    references to various types of posts or content in a social media or online context

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    502
    +0.15
    0.9%
    464
    +0.11
    0.6%
    436
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.15
    0.03
    464
    +0.11
    0.02
    154
    +0.10
    0.02
    Negative Logits
    §
    -2.40
    ĥ½
    -2.38
    ĸ´
    -2.33
    Į
    -2.33
    ľĵ
    -2.30
    ³
    -2.27
    Ĵ
    -2.26
    ķ
    -2.23
    ¥
    -2.21
    ģ
    -2.19
    POSITIVE LOGITS
    gres
    3.08
    mortem
    2.61
    erior
    2.54
    doctoral
    2.36
    gre
    2.02
    master
    1.96
    nikov
    1.86
    hoc
    1.85
    ilion
    1.82
    modern
    1.82
    Activations Density 0.056%

    No Known Activations