© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31785
    Prev
    Next
    INDEX
    Explanations

    emotional and relational states related to disappointment and social interaction

    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
    186
    +0.18
    1.1%
    6
    +0.14
    0.8%
    94
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.18
    0.15
    56
    +0.14
    -0.04
    111
    +0.13
    0.15
    Negative Logits
    ¤
    -2.72
    Į
    -2.68
    Ĥ¬
    -2.60
    IJ
    -2.52
    ĨĴ
    -2.51
    ¸
    -2.50
    ¥
    -2.44
    Īĺ
    -2.36
    ķ
    -2.36
    ·¸
    -2.32
    POSITIVE LOGITS
     themselves
    2.45
     apart
    1.86
     together
    1.71
     abdom
    1.52
    thems
    1.50
     ankles
    1.50
     imagination
    1.46
     pockets
    1.46
     shoulders
    1.46
     they
    1.45
    Activations Density 5.164%

    No Known Activations