© 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. 28877
    Prev
    Next
    INDEX
    Explanations

    terms related to classifications and regulations in various 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
    255
    +0.15
    0.8%
    369
    +0.15
    0.8%
    294
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.06
    255
    +0.15
    0.06
    135
    +0.14
    0.06
    Negative Logits
    omy
    -1.81
    fulness
    -1.78
    ftware
    -1.73
    ptions
    -1.68
    rele
    -1.52
    abil
    -1.51
    culus
    -1.46
    acchar
    -1.45
    vereign
    -1.43
    apine
    -1.41
    POSITIVE LOGITS
    ĻĤ
    4.25
    ²
    4.18
    ¬
    4.00
    ↵↵
    3.96
    ↵
    3.96
    ↵
    3.96
    <|outofrange|>
    3.96
    3.96
    3.96
    3.96
    Activations Density 0.810%

    No Known Activations