© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24108
    Prev
    Next
    INDEX
    Explanations

    terms related to colorectal health and cancer

    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
    +0.19
    1.2%
    71
    +0.14
    0.8%
    468
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.04
    271
    +0.14
    0.01
    156
    +0.12
    0.03
    Negative Logits
     perfect
    -1.65
    usterity
    -1.64
     respectful
    -1.61
     teach
    -1.58
     GENERATED
    -1.55
     fierce
    -1.44
     pupils
    -1.43
     loud
    -1.43
     calm
    -1.41
    edes
    -1.39
    POSITIVE LOGITS
    issance
    2.08
    ulif
    1.73
    watson
    1.60
     disposal
    1.58
    hurst
    1.58
    caster
    1.55
    illac
    1.52
    brains
    1.45
    mans
    1.45
    wood
    1.42
    Activations Density 0.076%

    No Known Activations