© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11057
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and jargon

    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
    369
    +0.16
    0.9%
    368
    +0.14
    0.8%
    159
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.16
    0.08
    368
    +0.14
    0.05
    159
    +0.14
    0.07
    Negative Logits
    "}](#
    -2.18
    Ĥ
    -1.84
    \]]{}
    -1.77
    $.[]{
    -1.58
    |}
    -1.57
    ":{
    -1.54
    ~\]
    -1.53
     */
    -1.53
    |}\
    -1.46
    ]}
    -1.44
    POSITIVE LOGITS
    ubicin
    1.52
     certificates
    1.45
     honors
    1.43
     submissions
    1.39
     Report
    1.39
     certificate
    1.38
    ichlet
    1.35
     Appeals
    1.35
    hold
    1.35
     manslaughter
    1.35
    Activations Density 0.611%

    No Known Activations