© 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. 4-RES-SM
    11. 12501
    Prev
    Next
    INDEX
    Explanations

    elements related to location and spatial features

    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
    307
    +0.25
    1.4%
    412
    +0.17
    0.9%
    466
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.25
    0.20
    145
    +0.17
    0.12
    292
    +0.17
    0.16
    Negative Logits
    «
    -2.02
    ¿½
    -1.96
    Ĥ
    -1.89
    į
    -1.84
    ĩ
    -1.83
    ·¸
    -1.76
    ĻĤ
    -1.74
    Ĩ
    -1.74
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.73
    Ģ
    -1.70
    POSITIVE LOGITS
     rooms
    2.75
     doors
    2.73
     halls
    2.67
     campus
    2.57
     apartment
    2.57
     Plaza
    2.55
     caf
    2.53
     Hotel
    2.52
     buildings
    2.46
     hotel
    2.46
    Activations Density 4.524%

    No Known Activations