© 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. 4-RES-SM
    11. 13793
    Prev
    Next
    INDEX
    Explanations

    references to problems and issues in various contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    390
    +0.13
    0.7%
    274
    +0.12
    0.7%
    474
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.13
    0.05
    287
    +0.12
    0.04
    149
    +0.11
    0.03
    Negative Logits
    ¿
    -3.69
    ¼
    -3.59
    IJ
    -3.39
    »¿
    -3.35
    ·¸
    -3.33
    ¤
    -3.23
    Ń
    -3.22
    ¥
    -3.06
    ¿½
    -3.05
    Ĵ
    -3.01
    POSITIVE LOGITS
     solved
    2.62
     encountered
    2.57
     solving
    2.52
    atics
    2.50
     solver
    2.47
     faced
    2.38
    atically
    2.26
     plag
    2.07
     arising
    2.05
     facing
    2.02
    Activations Density 0.160%

    No Known Activations