© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-SM
    11. 11160
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and capabilities of products or systems

    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
    98
    +0.22
    1.3%
    156
    +0.20
    1.2%
    34
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.22
    0.55
    156
    +0.20
    0.43
    71
    +0.17
    0.37
    Negative Logits
    ĻĤ
    -2.07
     vomiting
    -2.02
    áĢ¬
    -1.94
     menstru
    -1.81
     breasts
    -1.80
     surname
    -1.78
    áĢ¯
    -1.73
     abortions
    -1.73
     raped
    -1.69
    urname
    -1.68
    POSITIVE LOGITS
     IoT
    2.56
     IEEE
    2.56
     implementations
    2.54
     scalable
    2.45
     implementation
    2.29
     automation
    2.23
     technologies
    2.20
     developers
    2.14
     deployment
    2.13
     IBM
    2.11
    Activations Density 2.533%

    No Known Activations