© 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. 27729
    Prev
    Next
    INDEX
    Explanations

    references to trips or journeys

    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%
    358
    +0.12
    0.7%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.04
    156
    +0.12
    0.04
    56
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.98
    ķ
    -2.51
    Ŀ
    -2.50
    Ļ
    -2.43
    Ń
    -2.38
    §
    -2.33
    ©
    -2.23
    Ĥ¬
    -2.19
    ŀ
    -2.16
    ļ
    -2.14
    POSITIVE LOGITS
    henyl
    1.75
    ees
    1.59
    wright
    1.56
    port
    1.51
    pler
    1.49
    !(
    1.48
    nik
    1.47
    nam
    1.44
    go
    1.42
    odes
    1.41
    Activations Density 0.316%

    No Known Activations