© 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. MLP Post
    9. 2-MLP-SM
    11. 25466
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and their categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    436
    +0.14
    0.7%
    156
    +0.12
    0.7%
    177
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    0.06
    421
    +0.12
    0.05
    467
    +0.12
    0.03
    Negative Logits
     ([**
    -1.60
    onson
    -1.54
     mistrial
    -1.47
    cias
    -1.46
    imab
    -1.46
    **:
    -1.45
    inas
    -1.44
    ``
    -1.44
     ([@
    -1.44
    :--
    -1.41
    POSITIVE LOGITS
    ward
    2.08
    noon
    1.68
    wards
    1.66
     attention
    1.40
    oven
    1.38
    ...]
    1.36
    ational
    1.34
    coming
    1.31
    arily
    1.30
    leep
    1.29
    Activations Density 0.482%

    No Known Activations