© 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. 13453
    Prev
    Next
    INDEX
    Explanations

    references to misogyny and related concepts

    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
    59
    +0.17
    0.9%
    357
    +0.11
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.17
    0.02
    59
    +0.11
    0.02
    257
    +0.11
    0.02
    Negative Logits
     court
    -1.81
     injured
    -1.65
    aintiff
    -1.64
     weeks
    -1.43
     misplaced
    -1.41
     prosec
    -1.41
     victims
    -1.39
     appointments
    -1.38
     succession
    -1.38
     cases
    -1.38
    POSITIVE LOGITS
    ¾
    3.25
    ¹
    3.06
    ĻĤ
    3.05
    «
    2.89
    ¦
    2.79
    ±
    2.70
    °
    2.64
    ª
    2.59
    ´
    2.58
    ¸
    2.58
    Activations Density 0.148%

    No Known Activations