© 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. 1-RES-SM
    11. 26631
    Prev
    Next
    INDEX
    Explanations

    references to specific criteria and eligibility requirements

    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
    376
    +0.13
    0.7%
    365
    +0.12
    0.7%
    287
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.13
    0.01
    9
    +0.12
    0.01
    498
    +0.12
    0.01
    Negative Logits
    §
    -2.63
    ½
    -2.59
    »¿
    -2.58
    č↵
    -2.43
    ↵↵
    -2.43
    ↵↵
    -2.43
    -2.43
    -2.43
    ↵
    -2.43
    č↵
    -2.43
    POSITIVE LOGITS
     approval
    1.61
    atum
    1.53
     approved
    1.51
    less
    1.51
    Release
    1.50
     align
    1.48
    optic
    1.46
     override
    1.44
    entry
    1.43
    orbent
    1.42
    Activations Density 0.051%

    No Known Activations