© 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. 9739
    Prev
    Next
    INDEX
    Explanations

    references to forms or form-related structures

    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
    93
    +0.12
    0.6%
    25
    +0.11
    0.6%
    415
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.12
    0.01
    213
    +0.11
    0.03
    509
    +0.11
    0.03
    Negative Logits
     distances
    -1.77
    ness
    -1.73
    sburg
    -1.69
     skies
    -1.69
     distance
    -1.61
    keit
    -1.55
    terday
    -1.55
    woke
    -1.44
     seasons
    -1.43
     coast
    -1.40
    POSITIVE LOGITS
    ulating
    3.22
    idable
    3.02
    atted
    2.81
    ative
    2.81
    ulas
    2.56
    ality
    2.56
    atter
    2.55
    ats
    2.44
    ular
    2.29
    ulator
    2.25
    Activations Density 0.200%

    No Known Activations