© 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. 25627
    Prev
    Next
    INDEX
    Explanations

    pieces of information related to software development and programming functionalities

    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
    80
    +0.13
    0.7%
    201
    +0.12
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.13
    0.05
    376
    +0.12
    0.04
    201
    +0.11
    0.02
    Negative Logits
     stret
    -1.58
    IJ
    -1.55
     synthase
    -1.49
     suspended
    -1.37
     leading
    -1.34
     synthe
    -1.32
    —"
    -1.32
     oxidase
    -1.31
     fibrous
    -1.30
     vacant
    -1.30
    POSITIVE LOGITS
    respect
    1.74
    eston
    1.67
    uates
    1.65
    jee
    1.61
    matches
    1.59
    ittal
    1.56
    uance
    1.54
    sense
    1.53
    pson
    1.52
    dom
    1.51
    Activations Density 0.339%

    No Known Activations