© 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. 4-RES-SM
    6. 11566
    Prev
    Next
    INDEX
    Explanations

    intensifiers that amplify the degree or quality of an adjective

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.16
    0.9%
    67
    +0.14
    0.8%
    394
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.16
    0.04
    375
    +0.14
    0.06
    387
    +0.14
    0.07
    Negative Logits
    ĥ½
    -2.58
    Ĩ
    -2.55
    £
    -2.53
    ŀ
    -2.23
    Ļª
    -2.20
    ĨĴ
    -2.15
    ij
    -2.00
    ļ
    -1.97
    ĥ
    -1.93
    ¡
    -1.92
    POSITIVE LOGITS
     rare
    2.10
     few
    1.91
     intelligent
    1.84
     talented
    1.83
     nice
    1.81
     uncommon
    1.79
     unusual
    1.79
     easy
    1.79
    minded
    1.78
     much
    1.78
    Activations Density 0.142%

    No Known Activations