© 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. 12525
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their associated attributes

    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
    78
    +0.15
    0.8%
    255
    +0.12
    0.7%
    484
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.15
    0.03
    411
    +0.12
    0.05
    255
    +0.11
    0.00
    Negative Logits
     (“
    -2.09
    .]{}
    -1.85
     ðŁĻĤ
    -1.71
    ycin
    -1.70
    ]{},
    -1.67
    .),
    -1.63
    \.
    -1.59
     MERCHANTABILITY
    -1.57
     laboratories
    -1.56
    .:
    -1.56
    POSITIVE LOGITS
    Ļª
    4.02
    ">
    3.44
    "></
    3.27
    ij
    3.26
    µ
    3.23
    ĩ
    3.20
    ¬
    3.19
    į
    3.18
    ¾
    3.18
    ¡
    3.15
    Activations Density 0.398%

    No Known Activations