© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    topics related to essay writing, particularly in the context of English and educational material

    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
    192
    +0.14
    0.8%
    478
    +0.14
    0.7%
    68
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.14
    0.00
    95
    +0.14
    0.06
    192
    +0.13
    -0.02
    Negative Logits
    ¿½
    -3.02
    »¿
    -2.68
    ª
    -2.65
    ¶
    -2.56
    Ĭ
    -2.47
    ·
    -2.42
    ĸ
    -2.36
    Ĺ
    -2.32
    ´
    -2.31
    Ħ
    -2.29
    POSITIVE LOGITS
     writing
    3.88
     Writing
    3.76
     write
    3.68
     Writers
    3.66
     writers
    3.59
     Write
    3.45
     prose
    3.42
     poems
    3.35
     Writer
    3.32
     Poetry
    3.30
    Activations Density 1.868%

    No Known Activations