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. 28949
    Prev
    Next
    INDEX
    Explanations

    references to the brain and its conditions

    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
    156
    +0.24
    1.4%
    188
    +0.14
    0.8%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.24
    0.01
    446
    +0.14
    0.01
    299
    +0.14
    0.01
    Negative Logits
    ment
    -1.74
    ments
    -1.67
    aturday
    -1.59
     Khan
    -1.58
    umbent
    -1.57
    sible
    -1.53
    ftware
    -1.48
     online
    -1.41
     ÏĮÏĦι
    -1.40
     haste
    -1.39
    POSITIVE LOGITS
    stem
    2.11
    storm
    1.99
    wash
    1.77
    iac
    1.71
     parench
    1.70
    waves
    1.65
    wide
    1.62
    scape
    1.61
    sheet
    1.58
    washed
    1.53
    Activations Density 0.051%

    No Known Activations