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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29757
    Prev
    Next
    INDEX
    Explanations

    terms related to laboratory techniques and methodologies in biological research

    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
    471
    +0.13
    0.7%
    282
    +0.12
    0.6%
    100
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.02
    471
    +0.12
    0.01
    47
    +0.10
    0.02
    Negative Logits
    ĥ½
    -2.70
    »
    -2.67
    Ĭ
    -2.62
    Ľ
    -2.56
    ½
    -2.47
    ĸ
    -2.46
    ļ
    -2.46
    §
    -2.45
    ¹
    -2.41
    ī
    -2.40
    POSITIVE LOGITS
     tomography
    1.76
     analysis
    1.73
     characterization
    1.71
    PLC
    1.64
    lication
    1.60
     quantification
    1.57
    hemat
    1.55
     results
    1.53
    ETHOD
    1.52
    METHOD
    1.51
    Activations Density 0.121%

    No Known Activations