© 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. 12820
    Prev
    Next
    INDEX
    Explanations

    phrases indicating states of being or descriptions of 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
    395
    +0.15
    0.9%
    44
    +0.15
    0.8%
    231
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.15
    0.07
    44
    +0.15
    0.06
    430
    +0.13
    0.05
    Negative Logits
    ĻĤ
    -4.24
    Ļª
    -3.06
    ±
    -2.99
    »¿
    -2.72
    ©
    -2.69
    ĭ
    -2.66
    Ģ
    -2.61
    ¸
    -2.58
    ¿½
    -2.58
    Īĺ
    -2.58
    POSITIVE LOGITS
    rogenic
    1.52
     tolerated
    1.51
    olev
    1.46
    ochrom
    1.46
    ylated
    1.45
    ofl
    1.44
     extensively
    1.44
    olan
    1.41
    pecific
    1.41
     least
    1.40
    Activations Density 0.467%

    No Known Activations