© 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. 1-RES-SM
    11. 28328
    Prev
    Next
    INDEX
    Explanations

    terms related to sequencing in genetics

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.17
    1.0%
    376
    +0.14
    0.8%
    173
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.17
    0.01
    230
    +0.14
    0.02
    382
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.75
    §
    -2.09
    ĥ
    -2.01
    Ļª
    -1.85
    ³
    -1.83
    ĵ
    -1.76
    ľĵ
    -1.71
    ¯
    -1.69
    ´
    -1.69
    ī
    -1.68
    POSITIVE LOGITS
    anium
    1.61
    cie
    1.55
    haus
    1.44
     primers
    1.40
    etable
    1.37
    antha
    1.33
    ientos
    1.32
     transcript
    1.31
    ester
    1.30
    ethyl
    1.30
    Activations Density 0.072%

    No Known Activations