© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12504
    Prev
    Next
    INDEX
    Explanations

    references to post-operative periods and processes related to medical treatments

    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
    18
    +0.13
    0.7%
    436
    +0.12
    0.7%
    310
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.13
    0.03
    172
    +0.12
    0.03
    511
    +0.11
    0.02
    Negative Logits
    rapeut
    -2.07
    ANNEL
    -1.82
     extent
    -1.78
    TTP
    -1.72
    ffect
    -1.71
    ãģŁãĤģ
    -1.64
     plain
    -1.63
    Inflater
    -1.60
    OULD
    -1.60
    Equal
    -1.50
    POSITIVE LOGITS
    mortem
    2.38
    gres
    2.14
    doctoral
    1.99
     hoc
    1.98
    ulates
    1.98
    bellum
    1.77
    nikov
    1.77
    erior
    1.75
    ondo
    1.72
    modern
    1.65
    Activations Density 0.050%

    No Known Activations