Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27416
    Prev
    Next
    INDEX
    Explanations

    keywords related to a software framework or programming structure

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    156
    +0.20
    1.2%
    71
    +0.12
    0.8%
    173
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.01
    469
    +0.12
    0.01
    26
    +0.11
    0.01
    Negative Logits
    woke
    -2.01
     Virgin
    -1.79
     deceased
    -1.69
     gay
    -1.63
    sed
    -1.62
     obese
    -1.62
     homosexual
    -1.57
    res
    -1.51
     toast
    -1.49
     euthan
    -1.48
    POSITIVE LOGITS
    "}](#
    2.07
    istry
    1.89
    ĸ
    1.82
    ULAR
    1.81
    CHA
    1.73
    cript
    1.70
     repertoire
    1.69
    erve
    1.67
    hel
    1.66
    Script
    1.61
    Activations Density 0.012%

    No Known Activations