© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28607
    Prev
    Next
    INDEX
    Explanations

    the article "an."

    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
    171
    +0.13
    0.7%
    377
    +0.13
    0.7%
    8
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.13
    0.05
    377
    +0.13
    0.07
    436
    +0.12
    0.06
    Negative Logits
    limits
    -1.61
    nolimits
    -1.61
    ments
    -1.56
    æł¼
    -1.55
     fame
    -1.51
    illi
    -1.51
    pering
    -1.46
    аÑģÑģ
    -1.44
    vet
    -1.44
     reductase
    -1.43
    POSITIVE LOGITS
    µ
    2.76
    ¦
    2.73
    ĩ
    2.70
    º
    2.68
    ©
    2.65
    ·
    2.64
    ¹
    2.61
    IJ
    2.55
    »¿
    2.53
    Ĥ
    2.52
    Activations Density 0.241%

    No Known Activations