© 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. 24411
    Prev
    Next
    INDEX
    Explanations

    instances and examples of various concepts or items within text

    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
    31
    +0.15
    0.9%
    152
    +0.13
    0.7%
    165
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.15
    0.03
    363
    +0.13
    0.03
    475
    +0.13
    0.03
    Negative Logits
    Ļ
    -2.10
    Ĭ
    -2.05
    ĥ
    -1.88
    ³
    -1.72
    ´
    -1.72
    ŀ
    -1.68
    ĵ
    -1.67
    Ħ
    -1.66
    Ľ
    -1.65
    ļ
    -1.64
    POSITIVE LOGITS
    ']);
    1.59
    ql
    1.53
    ")]
    1.53
    oner
    1.50
    ))\
    1.50
     hers
    1.48
     yours
    1.47
    together
    1.46
    !\
    1.46
    arently
    1.45
    Activations Density 0.280%

    No Known Activations