© 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. 2-RES-SM
    11. 29985
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and data structures

    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
    419
    +0.13
    0.8%
    121
    +0.13
    0.7%
    105
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.12
    46
    +0.13
    0.02
    102
    +0.12
    0.05
    Negative Logits
     GmbH
    -1.56
    iol
    -1.48
     controller
    -1.46
    pressed
    -1.46
    ylase
    -1.46
     safety
    -1.45
    ervation
    -1.37
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -1.32
    use
    -1.31
    Verlag
    -1.26
    POSITIVE LOGITS
     thanks
    1.80
     deserve
    1.58
     admit
    1.49
     soph
    1.44
     cm
    1.34
     deserves
    1.32
    fon
    1.31
     dilated
    1.29
    vae
    1.29
    omonas
    1.28
    Activations Density 6.162%

    No Known Activations