© 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. 1-RES-SM
    11. 27562
    Prev
    Next
    INDEX
    Explanations

    specific types of formatting or structure within the document

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    55
    +0.12
    0.7%
    355
    +0.11
    0.6%
    142
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.20
    271
    +0.11
    0.10
    156
    +0.10
    0.09
    Negative Logits
    >::
    -1.76
    *>
    -1.68
     >::
    -1.67
     ]$
    -1.55
     husband
    -1.52
    quez
    -1.50
    htra
    -1.39
    inated
    -1.38
    imb
    -1.37
     say
    -1.36
    POSITIVE LOGITS
    ļ
    1.80
    º
    1.73
    Į
    1.71
    Ĺ
    1.67
    ¡
    1.66
    ł
    1.66
    ·¸
    1.64
    ĸ
    1.64
    Ĵ
    1.64
    Ľ
    1.57
    Activations Density 0.117%

    No Known Activations