© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    themes related to challenges and risks 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
    393
    +0.12
    0.7%
    198
    +0.12
    0.7%
    31
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.17
    2
    +0.12
    0.11
    91
    +0.11
    0.10
    Negative Logits
    Īĺ
    -2.90
    ĭ
    -2.67
    ħ
    -2.47
    £
    -2.35
    Ļª
    -2.29
    ¿
    -2.24
    İ
    -2.15
    <|outofrange|>
    -2.15
    ↵↵
    -2.15
    ↵
    -2.15
    POSITIVE LOGITS
    itiveness
    1.68
     bitterness
    1.62
    itism
    1.62
    eness
    1.60
    iousness
    1.59
    terness
    1.51
     attributable
    1.51
     happening
    1.51
    ificance
    1.49
     borne
    1.48
    Activations Density 3.465%

    No Known Activations