© 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 EvalsExportsAPI 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. 26385
    Prev
    Next
    INDEX
    Explanations

    SQL selection statements and related syntax

    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
    287
    +0.13
    0.7%
    307
    +0.13
    0.7%
    140
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.13
    0.02
    287
    +0.13
    0.02
    381
    +0.12
    0.01
    Negative Logits
    ĵ
    -3.44
    ĥ½
    -3.13
    ĩ
    -3.03
    ĥ
    -3.02
    ¤
    -3.02
    ľĵ
    -2.92
    Ľ
    -2.86
    ·¸
    -2.82
    İ
    -2.81
    ³
    -2.77
    POSITIVE LOGITS
    ivity
    2.24
    able
    2.20
    ably
    1.99
    ively
    1.88
     polls
    1.57
    iveness
    1.54
    ables
    1.51
    ive
    1.48
     one
    1.48
    ulous
    1.47
    Activations Density 0.031%

    No Known Activations