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. 27321
    Prev
    Next
    INDEX
    Explanations

    terms related to biological sciences or medical conditions

    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
    +0.18
    1.0%
    503
    +0.16
    0.9%
    148
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.18
    0.01
    86
    +0.16
    0.01
    294
    +0.14
    0.01
    Negative Logits
    ancel
    -1.77
    oxacin
    -1.59
    odal
    -1.57
    agle
    -1.54
    astern
    -1.53
    az
    -1.53
    agles
    -1.41
    raz
    -1.40
    dule
    -1.40
    ocus
    -1.39
    POSITIVE LOGITS
    fecture
    1.95
    istic
    1.86
    itat
    1.65
    istically
    1.63
    ele
    1.58
    ISPR
    1.58
    ĻĤ
    1.57
    isms
    1.55
     territory
    1.53
    weather
    1.51
    Activations Density 1.281%

    No Known Activations