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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12085
    Prev
    Next
    INDEX
    Explanations

    instances of definite and indefinite articles in different contexts

    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
    23
    +0.13
    0.7%
    436
    +0.13
    0.7%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.03
    436
    +0.13
    0.04
    464
    +0.13
    0.03
    Negative Logits
    à±į
    -1.94
    liga
    -1.63
    als
    -1.62
    Verlag
    -1.50
    nÃŃ
    -1.49
    regation
    -1.48
    ãĤīãĤĮ
    -1.47
    ãģ¦
    -1.47
    lement
    -1.46
    naire
    -1.45
    POSITIVE LOGITS
     alike
    2.39
     consequent
    2.01
     subsequent
    1.98
     others
    1.92
     combination
    1.75
     correspondingly
    1.69
     caution
    1.64
    ureus
    1.60
     forth
    1.56
     knowing
    1.56
    Activations Density 0.252%

    No Known Activations