© 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. 28614
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of doubt or negation

    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
    12
    +0.11
    0.6%
    43
    +0.10
    0.6%
    57
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.11
    0.04
    159
    +0.10
    0.04
    90
    +0.09
    0.03
    Negative Logits
    Īĺ
    -2.44
    ·¸
    -2.25
    »¿
    -2.24
    ¬
    -2.17
    ĸ´
    -2.17
    Ŀ
    -2.02
    °
    -1.97
    ©
    -1.96
    £
    -1.96
    º
    -1.91
    POSITIVE LOGITS
    taient
    1.98
     mistaken
    1.84
    ahoma
    1.72
    lessness
    1.58
     manifest
    1.49
     populations
    1.43
    mos
    1.43
     chase
    1.39
     chances
    1.34
    aches
    1.33
    Activations Density 0.492%

    No Known Activations