© 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. 9184
    Prev
    Next
    INDEX
    Explanations

    keywords related to permissions and agreements

    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
    78
    +0.16
    1.1%
    21
    +0.13
    0.8%
    271
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.16
    0.01
    490
    +0.13
    0.01
    229
    +0.12
    0.01
    Negative Logits
     headlines
    -1.64
     impression
    -1.40
    ered
    -1.31
     awe
    -1.28
    llo
    -1.27
     penalty
    -1.26
    rile
    -1.25
    gered
    -1.23
     Weekly
    -1.22
    cens
    -1.21
    POSITIVE LOGITS
    ª
    2.04
    ©
    1.93
    Ĵ
    1.79
    Ħ
    1.76
    ²
    1.75
    IJ
    1.75
    ĥ
    1.71
    ħ
    1.69
    ĵ
    1.62
    ĻĤ
    1.57
    Activations Density 0.041%

    No Known Activations