© 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. 4-RES-SM
    11. 12005
    Prev
    Next
    INDEX
    Explanations

    references to images and visual content

    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
    328
    +0.14
    0.8%
    497
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.14
    0.02
    483
    +0.14
    0.03
    189
    +0.13
    0.03
    Negative Logits
    ¼
    -2.33
    º
    -2.30
    ¿½
    -2.23
    ľĵ
    -2.19
    Īĺ
    -2.17
    ĵ
    -2.16
    ¯
    -2.15
    ł
    -2.10
    ´
    -2.09
    §
    -2.08
    POSITIVE LOGITS
     gallery
    2.55
     galleries
    2.47
     viewer
    2.23
     uploaded
    2.13
     img
    2.10
     caption
    2.08
    jpeg
    2.02
     captured
    1.99
     image
    1.98
     Caption
    1.93
    Activations Density 0.163%

    No Known Activations