© 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. 1-RES-SM
    11. 27891
    Prev
    Next
    INDEX
    Explanations

    variations of the word "form" in different 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/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
    389
    +0.14
    0.8%
    392
    +0.14
    0.8%
    172
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.14
    0.03
    389
    +0.14
    0.03
    172
    +0.13
    0.02
    Negative Logits
    ĻĤ
    -3.43
    ¯
    -2.93
    ½
    -2.80
    ľĵ
    -2.79
    ·
    -2.72
    ±
    -2.67
    ĸ´
    -2.66
    ·¸
    -2.61
    ¤
    -2.58
    Ń
    -2.57
    POSITIVE LOGITS
    idable
    2.60
    ulating
    2.44
    ative
    2.07
    ably
    1.99
    ics
    1.96
    ally
    1.96
    ulas
    1.89
    ulator
    1.88
    ality
    1.87
    nel
    1.87
    Activations Density 0.054%

    No Known Activations