© 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. 31371
    Prev
    Next
    INDEX
    Explanations

    XML or programming-related code elements and attributes

    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
    388
    +0.12
    0.7%
    371
    +0.11
    0.6%
    47
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.12
    -0.01
    185
    +0.11
    0.03
    21
    +0.11
    0.03
    Negative Logits
     ``
    -1.84
    listed
    -1.58
    ``
    -1.58
    80211
    -1.52
    ologies
    -1.46
    )):
    -1.46
     timeline
    -1.41
     supplier
    -1.40
    sequence
    -1.39
    discovery
    -1.36
    POSITIVE LOGITS
    ĥ½
    3.22
    Ļª
    3.19
    º
    3.06
    ´
    3.02
    ¾
    2.99
    ī
    2.94
    »¿
    2.89
    µ
    2.87
    ¿
    2.84
    Ń
    2.83
    Activations Density 0.620%

    No Known Activations