Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12216
    Prev
    Next
    INDEX
    Explanations

    words associated with discontent or dissatisfaction

    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
    127
    +0.15
    0.9%
    156
    +0.12
    0.7%
    360
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.15
    0.03
    360
    +0.12
    0.02
    172
    +0.12
    0.02
    Negative Logits
    ureus
    -2.08
    ños
    -1.55
    ^*$
    -1.49
    USD
    -1.42
    á½IJ
    -1.41
    eries
    -1.38
    "){
    -1.38
    orems
    -1.37
    aliana
    -1.36
    OPLE
    -1.31
    POSITIVE LOGITS
     induct
    1.66
    integr
    1.64
    ilin
    1.62
    hing
    1.56
    junction
    1.56
    ambiguation
    1.52
    integration
    1.46
    bourg
    1.43
     chromatography
    1.41
    ³
    1.39
    Activations Density 0.067%

    No Known Activations