© 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. 4-RES-SM
    11. 12134
    Prev
    Next
    INDEX
    Explanations

    medical terms related to blood disorders and hematology

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.25
    1.4%
    356
    +0.14
    0.8%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.25
    0.01
    218
    +0.14
    0.01
    18
    +0.13
    0.01
    Negative Logits
    watson
    -1.86
    ftware
    -1.71
    ESULT
    -1.55
    STM
    -1.44
    same
    -1.39
    blogger
    -1.33
     theirs
    -1.28
     constructor
    -1.28
    ações
    -1.28
    FTA
    -1.25
    POSITIVE LOGITS
    Ļ
    3.18
    ĸ
    3.06
    ĵ
    2.89
    Ķ
    2.85
    Ĥ
    2.84
    ģ
    2.84
    ĥ
    2.79
    Ĵ
    2.75
    ı
    2.69
    İ
    2.68
    Activations Density 0.033%

    No Known Activations