© 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. 13750
    Prev
    Next
    INDEX
    Explanations

    affirmative statements about conditions or qualities

    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
    23
    +0.21
    1.2%
    419
    +0.16
    1.0%
    394
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.10
    304
    +0.16
    0.07
    336
    +0.15
    0.07
    Negative Logits
    Ļª
    -3.43
    ±
    -3.14
    ©
    -3.10
    Ĥ¬
    -3.09
    ¸
    -2.91
    ļ
    -2.87
    ĭ
    -2.75
    ľĵ
    -2.74
    Ģ
    -2.71
    ĻĤ
    -2.70
    POSITIVE LOGITS
     additionally
    1.62
     imperative
    1.61
    amo
    1.58
     furthermore
    1.55
    uate
    1.53
     also
    1.51
     incumbent
    1.49
     finally
    1.48
    uca
    1.46
     likewise
    1.44
    Activations Density 0.604%

    No Known Activations