© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12130
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly streets and structures associated with urban settings

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    466
    +0.16
    0.9%
    309
    +0.16
    0.9%
    307
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.16
    0.04
    408
    +0.16
    0.03
    212
    +0.14
    0.04
    Negative Logits
    etic
    -1.73
    ise
    -1.56
    missions
    -1.55
     otherwise
    -1.53
    ifiable
    -1.43
    "}*
    -1.42
    erably
    -1.41
    ethe
    -1.40
    eness
    -1.40
    issions
    -1.39
    POSITIVE LOGITS
    lights
    2.19
    corner
    2.05
    car
    1.92
     Fighter
    1.91
    cars
    1.82
     NW
    1.81
    lam
    1.76
    wise
    1.73
     corner
    1.73
     Mall
    1.69
    Activations Density 0.416%

    No Known Activations