© 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. 24734
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue within the text

    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
    156
    +0.24
    1.4%
    17
    +0.23
    1.3%
    233
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.24
    0.08
    100
    +0.23
    0.07
    17
    +0.12
    0.04
    Negative Logits
    ologies
    -1.71
    ological
    -1.65
    omatic
    -1.64
    ostat
    -1.56
    osal
    -1.52
    ology
    -1.51
    ↵↵↵↵↵
    -1.41
    ometer
    -1.37
    doibase
    -1.36
     toll
    -1.33
    POSITIVE LOGITS
    ¼
    2.30
    ĭ
    2.15
    ®
    2.03
    ĥ
    1.99
    Ĭ
    1.90
    §
    1.85
    ½
    1.77
    ŀ
    1.74
    ģ
    1.72
    ¹
    1.70
    Activations Density 0.780%

    No Known Activations