© 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. 24467
    Prev
    Next
    INDEX
    Explanations

    terms related to relative and absolute comparisons, especially in the context of assessments or evaluations

    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
    376
    +0.14
    0.8%
    129
    +0.13
    0.7%
    503
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.02
    129
    +0.13
    0.01
    500
    +0.11
    0.02
    Negative Logits
    Ĵ
    -2.13
    «
    -2.10
    Ĥ¬
    -1.97
    ansen
    -1.95
    ert
    -1.89
    »¿
    -1.88
    ire
    -1.81
    Ķ
    -1.77
    Ļ
    -1.77
    eton
    -1.76
    POSITIVE LOGITS
    ties
    2.02
     humidity
    1.52
    culos
    1.52
    liest
    1.51
     heights
    1.43
     positions
    1.41
     clocks
    1.41
     clock
    1.40
     abundances
    1.39
    ök
    1.39
    Activations Density 0.100%

    No Known Activations