© 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. 1-RES-SM
    11. 28385
    Prev
    Next
    INDEX
    Explanations

    variations of the term "aggressive" or terms indicating aggression

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    465
    +0.15
    0.9%
    506
    +0.13
    0.7%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.15
    0.00
    482
    +0.13
    0.00
    10
    +0.13
    0.00
    Negative Logits
    â
    -1.64
     Away
    -1.40
    oprotein
    -1.35
     manifest
    -1.33
    rs
    -1.33
    eds
    -1.31
    opath
    -1.31
     detail
    -1.31
    ward
    -1.30
     trait
    -1.27
    POSITIVE LOGITS
    ¦
    2.34
    »
    2.15
    ¨
    2.06
    Īĺ
    1.98
    ¾
    1.97
    Ĵ
    1.85
    ¹
    1.77
    ľĵ
    1.76
    ¸
    1.75
    ĻĤ
    1.74
    Activations Density 0.000%

    No Known Activations