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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27112
    Prev
    Next
    INDEX
    Explanations

    references to forms in coding or web development

    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
    392
    +0.13
    0.8%
    172
    +0.12
    0.7%
    10
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.02
    335
    +0.12
    0.02
    470
    +0.11
    0.02
    Negative Logits
    unnumbered
    -2.53
    woke
    -1.98
     MERCHANTABILITY
    -1.75
     same
    -1.64
    ¯
    -1.61
    ĥ
    -1.60
    terday
    -1.60
    ¶
    -1.58
    ½
    -1.54
    ·¸
    -1.52
    POSITIVE LOGITS
    idable
    3.05
    atted
    2.57
    ulator
    2.08
    ulation
    2.07
    ulated
    2.06
    ats
    2.02
    ulas
    2.02
    works
    2.00
    eless
    1.97
    ulators
    1.96
    Activations Density 0.053%

    No Known Activations