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

    Neuronpedia

    Jacobian LensNEW
    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. 11234
    Prev
    Next
    INDEX
    Explanations

    terms related to medical imaging and vascular 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/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
    +0.16
    0.9%
    244
    +0.13
    0.7%
    18
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.16
    0.02
    218
    +0.13
    0.02
    21
    +0.10
    0.01
    Negative Logits
    er
    -1.91
     interest
    -1.81
    mith
    -1.49
     unpublished
    -1.46
    eren
    -1.45
     generality
    -1.44
    bred
    -1.42
    ercase
    -1.42
     COPYRIGHT
    -1.40
    ftware
    -1.38
    POSITIVE LOGITS
    ħ
    3.79
    Ļ
    3.74
    ³
    3.43
    ¦
    3.38
    Ĵ
    3.36
    Ĩ
    3.23
    ı
    3.20
    Ľ
    3.19
    Ĥ
    3.19
    ł
    3.17
    Activations Density 0.081%

    No Known Activations