© 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. 27096
    Prev
    Next
    INDEX
    Explanations

    references to "things" and general concepts

    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
    434
    +0.14
    0.7%
    365
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.14
    0.03
    305
    +0.12
    0.02
    78
    +0.12
    0.03
    Negative Logits
    rency
    -1.88
    ureus
    -1.52
    igating
    -1.48
    express
    -1.46
    eration
    -1.41
    igon
    -1.39
     ©
    -1.38
    rano
    -1.36
     Mumbai
    -1.36
    ancer
    -1.33
    POSITIVE LOGITS
    ģ
    1.68
     dice
    1.64
    nel
    1.60
    iop
    1.47
    meal
    1.46
    binding
    1.44
    ½
    1.44
    nell
    1.43
    ies
    1.42
    ĻĤ
    1.40
    Activations Density 0.117%

    No Known Activations