© 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. 4-RES-SM
    11. 9532
    Prev
    Next
    INDEX
    Explanations

    references to urban development and planning projects

    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
    137
    +0.13
    0.7%
    171
    +0.13
    0.7%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.13
    0.11
    288
    +0.13
    0.10
    171
    +0.12
    0.07
    Negative Logits
     tumour
    -3.48
     tumours
    -3.04
     haem
    -2.83
     recognise
    -2.71
     randomised
    -2.70
     realised
    -2.67
     behaviour
    -2.66
     haemat
    -2.63
     realise
    -2.62
     anaest
    -2.62
    POSITIVE LOGITS
     Township
    2.92
     Interstate
    2.92
     Arkansas
    2.82
     downtown
    2.79
     statewide
    2.77
     Wyoming
    2.75
     Railroad
    2.67
     Idaho
    2.64
     railroad
    2.63
     Colorado
    2.60
    Activations Density 2.345%

    No Known Activations