© 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. 10952
    Prev
    Next
    INDEX
    Explanations

    numerical data and values, particularly in a technical or regulatory 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/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
    240
    +0.17
    1.0%
    186
    +0.15
    0.9%
    99
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.17
    0.13
    99
    +0.15
    0.10
    464
    +0.14
    0.03
    Negative Logits
     intercourse
    -1.59
     bride
    -1.55
     sep
    -1.53
     burnt
    -1.52
    ylum
    -1.46
    "_
    -1.42
     '.
    -1.40
     specimens
    -1.40
    "]
    -1.39
    ze
    -1.39
    POSITIVE LOGITS
     CMB
    1.71
     broadly
    1.68
     cytokine
    1.61
     analyses
    1.56
     studies
    1.53
     assessments
    1.47
     accountable
    1.46
     primarily
    1.46
     chemok
    1.42
     fuels
    1.41
    Activations Density 5.518%

    No Known Activations