© 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. 28217
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related references

    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
    271
    +0.17
    1.0%
    198
    +0.15
    0.9%
    442
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.21
    156
    +0.15
    0.21
    71
    +0.13
    0.20
    Negative Logits
     career
    -1.45
    cases
    -1.30
    med
    -1.30
     Campaign
    -1.29
    pecific
    -1.27
     lane
    -1.27
    izations
    -1.27
    nement
    -1.23
    icable
    -1.22
    ÃŃa
    -1.22
    POSITIVE LOGITS
    textup
    1.56
    tml
    1.47
    ribe
    1.44
    áĢº
    1.43
    lang
    1.41
    ап
    1.40
    ounge
    1.39
    ocrates
    1.36
    ÑĢÑĥг
    1.35
    ีà¹Ī
    1.34
    Activations Density 2.080%

    No Known Activations