© 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. 2-RES-SM
    11. 27800
    Prev
    Next
    INDEX
    Explanations

    references to job opportunities and employment-related 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
    57
    +0.14
    0.8%
    248
    +0.13
    0.7%
    285
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.14
    0.12
    248
    +0.13
    0.12
    285
    +0.12
    0.14
    Negative Logits
    toString
    -1.86
    ously
    -1.52
    innerHTML
    -1.52
    еÑĤ
    -1.47
    Ñĥж
    -1.44
     brow
    -1.44
    (()
    -1.41
    ipation
    -1.40
    Unmarshal
    -1.37
    hljs
    -1.36
    POSITIVE LOGITS
    journal
    1.78
    /~
    1.60
     arb
    1.59
     emergencies
    1.44
    ystems
    1.42
    1371
    1.41
    8080
    1.39
     living
    1.38
    :`
    1.37
     arrangements
    1.37
    Activations Density 4.843%

    No Known Activations