© 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. 28029
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the text

    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
    110
    +0.15
    0.8%
    491
    +0.11
    0.6%
    457
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    0.03
    110
    +0.11
    0.02
    82
    +0.10
    0.03
    Negative Logits
    ¦
    -2.54
    ¤
    -2.37
    ģ
    -2.34
    ĸ´
    -2.31
    ¸
    -2.27
    ®
    -2.25
    ¶
    -2.25
    ķ
    -2.23
    ´
    -2.22
    ²
    -2.16
    POSITIVE LOGITS
    ycl
    1.96
    aine
    1.92
    apo
    1.87
    thur
    1.78
    lin
    1.76
    izumab
    1.71
    bourne
    1.66
    nier
    1.62
    nai
    1.58
    ala
    1.57
    Activations Density 0.048%

    No Known Activations