© 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. 29228
    Prev
    Next
    INDEX
    Explanations

    questions related to possibility and permissibility

    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
    23
    +0.15
    0.9%
    195
    +0.13
    0.8%
    478
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.15
    0.02
    390
    +0.13
    0.03
    449
    +0.13
    0.01
    Negative Logits
    Ł
    -2.07
    ħ
    -2.04
    Ļ
    -1.86
    Ļª
    -1.85
    ieri
    -1.84
    ¡
    -1.81
    ¼
    -1.81
    ľ
    -1.81
    ®
    -1.79
    ´
    -1.79
    POSITIVE LOGITS
     anything
    1.70
    opically
    1.69
    ?’
    1.65
    ]>
    1.64
    okinetic
    1.61
     differences
    1.59
    olated
    1.52
     discriminate
    1.50
     yours
    1.45
     uncomfortable
    1.44
    Activations Density 0.468%

    No Known Activations