© 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 EvalsExportsinterp-engineNEWAPI 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. 31471
    Prev
    Next
    INDEX
    Explanations

    snippets related to programming or code structure

    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
    210
    +0.16
    0.9%
    248
    +0.14
    0.8%
    153
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.16
    0.18
    176
    +0.14
    0.17
    160
    +0.13
    0.15
    Negative Logits
    avi
    -1.48
    osus
    -1.47
    ubation
    -1.41
    iev
    -1.41
     Vienna
    -1.35
    berger
    -1.34
     disability
    -1.33
     "";
    -1.33
     measles
    -1.32
     gesture
    -1.31
    POSITIVE LOGITS
    ľĵ
    1.96
    atte
    1.51
     sources
    1.45
     venues
    1.41
    agraph
    1.41
    rolet
    1.39
    cdn
    1.38
     competent
    1.36
    pshire
    1.35
    »¿
    1.35
    Activations Density 7.505%

    No Known Activations