© 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. 2-RES-SM
    11. 10031
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related terminology, especially used in documentation or technical contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    204
    +0.17
    1.0%
    198
    +0.15
    0.9%
    353
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.17
    0.16
    100
    +0.15
    0.14
    268
    +0.12
    0.13
    Negative Logits
     career
    -1.56
    landers
    -1.55
    overs
    -1.44
     tourism
    -1.43
    vet
    -1.39
     education
    -1.35
    dose
    -1.35
    ribute
    -1.34
     mission
    -1.34
     morale
    -1.33
    POSITIVE LOGITS
    duced
    1.57
    endix
    1.40
     tubes
    1.39
     sino
    1.38
     instead
    1.37
     sockets
    1.32
    stra
    1.31
    eld
    1.30
    arlier
    1.27
    ided
    1.27
    Activations Density 6.386%

    No Known Activations